diff --git a/README.md b/README.md index 7be5fc7f47d5db027d120b8024982df93db95b74..14455763d1ccc1e7eb054008b596b931c82b9c07 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,141 @@ --- license: mit --- + +# Tau LLM Unity ML Agents Project + +Welcome to the Tau LLM Unity ML Agents Project repository! This project focuses on training reinforcement learning agents using Unity ML-Agents and the PPO algorithm. Our goal is to optimize the performance of the agents through various configurations and training runs. + +## Project Overview + +This repository contains the code and configurations for training agents in a Unity environment using the Proximal Policy Optimization (PPO) algorithm. The agents are designed to learn and adapt to their environment, improving their performance over time. + +### Key Features + +- **Reinforcement Learning**: Utilizes the PPO algorithm for training agents. +- **Unity ML-Agents**: Integrates with Unity ML-Agents for a seamless training experience. +- **Custom Reward Functions**: Implements gradient-based reward functions for nuanced feedback. +- **Memory Networks**: Incorporates memory networks to handle temporal dependencies. +- **TensorBoard Integration**: Monitors training progress and performance using TensorBoard. + +## Configuration + +Below is the configuration used for training the agents: + +```yaml +behaviors: + TauAgent: + trainer_type: ppo + hyperparameters: + batch_size: 256 + buffer_size: 4096 + learning_rate: 0.00003 + beta: 0.005 + epsilon: 0.2 + lambd: 0.95 + num_epoch: 10 + learning_rate_schedule: linear + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: + memory_size: 256 + sequence_length: 256 + num_layers: 4 + reward_signals: + extrinsic: + gamma: 0.99 + strength: 1.0 + curiosity: + gamma: 0.995 + strength: 0.1 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + learning_rate: 0.00003 + keep_checkpoints: 10 + checkpoint_interval: 100000 + threaded: true + max_steps: 3000000 + time_horizon: 256 + summary_freq: 10000 +``` + +## Model Naming Convention + +The models in this repository follow the naming convention `Tau__`. This helps in easily identifying the series and the number of training steps for each model. + +## Getting Started + +### Prerequisites + +- Unity 6 +- Unity ML-Agents Toolkit +- Python 3.10.11 +- PyTorch +- Transformers + +### Installation + +1. Clone the repository: + ```bash + git clone https://github.com/yourusername/tau-llm-unity-ml-agents.git + cd tau-llm-unity-ml-agents + ``` + +2. Install the required Python packages: + ```bash + pip install -r requirements.txt + ``` + +3. Open the Unity project: + - Launch Unity Hub and open the project folder. + +### Training the Agent + +To start training the agent, run the following command: +```bash +mlagents-learn config/trainer_config.yaml --run-id=run1 +``` + +### Monitoring Training + +You can monitor the training progress using TensorBoard: +```bash +tensorboard --logdir=results --port=6006 +``` + +## Results + +The training results, including the average reward and cumulative reward, can be visualized using TensorBoard. The graphs below show the performance of the agent over time: + +![Average Reward](path/to/average_reward.png) +![Cumulative Reward](path/to/cumulative_reward.png) + +## Citation + +If you use this project in your research, please cite it as follows: + +```bibtex +@misc{Tau, + author = {K. Rawson}, + title = {Tau LLM Unity ML Agents Project}, + year = {2024}, + publisher = {GitHub}, + journal = {GitHub repository}, + howpublished = {\url{https://github.com/p3nGu1nZz/Tau}}, +} +``` + +## License + +This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details. + +## Acknowledgments + +- Unity ML-Agents Toolkit +- TensorFlow and PyTorch communities +- Hugging Face for hosting the model repository \ No newline at end of file diff --git a/results/tau_agent_A1_2M/Tau-A1-2M.onnx b/results/tau_agent_A1_2M/Tau-A1-2M.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d8c54ebc3ed23996dd2fb8d86eb7e9b4ce665fc3 --- /dev/null +++ b/results/tau_agent_A1_2M/Tau-A1-2M.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08931e19cffa93c14fed86e9bb88278424715303928d4761bf3dcc257fdde73d +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1199744.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1199744.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8d606638a8ef97ba5e21c2e9003eeb68b5864fdc --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1199744.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24d7a70f3f708362ccd3b35ccbf309d81696c379a5c2111810676ffda6c9c3d +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1199744.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1199744.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee92c8dcd75404e196102f591ec1884d9fd0af71 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1199744.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f556a11f0fea58e2cc679cf2f9ad6e86403425ced6496f25188080f8f29bc8e +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1299958.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1299958.onnx new file mode 100644 index 0000000000000000000000000000000000000000..f7e7317432d5bae12b8e4a8321eba2ca497a3509 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1299958.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6f5d1ee696b00963d7cb00a10b924fdf123f5eb46b618ba006117c7d843919 +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1299958.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1299958.pt new file mode 100644 index 0000000000000000000000000000000000000000..b97d29cb84f7a36bb2fc71cfcf1227ff78e08f96 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1299958.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c0244046f46126c14c82f60ef46b799325fb0f35205cec04ccec9141784a93c +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1399744.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1399744.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9b3b391962a7c6bb67039a2ef64feace89287ea0 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1399744.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0b419212303e89f05b6d735d04bb392166df4dd491fd0036ea2fce40a3abd6 +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1399744.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1399744.pt new file mode 100644 index 0000000000000000000000000000000000000000..da6cb7ae61e7025a337b4332a8ddcdfe9b771893 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1399744.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c120a1fa8108b6b9558d9667fe949808b3e16394d499693e20392d2ea1f6c28e +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1499776.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1499776.onnx new file mode 100644 index 0000000000000000000000000000000000000000..2a4b9acd9b3bfbe783bde7a3bbb71cc68c6ac9cd --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1499776.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f424ea2d9e633119050d04d95e1079bee5e8c3a1a9fee31282ca95855bd7d885 +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1499776.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1499776.pt new file mode 100644 index 0000000000000000000000000000000000000000..c7a61989ddd1c6f293f5aa8bc5a80f7c5725fc3c --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1499776.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912696d11a6837fc71783e311bed38195e1dda57fe4123a64141db5e96083ba3 +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1599808.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1599808.onnx new file mode 100644 index 0000000000000000000000000000000000000000..dc1acac74fcccbc7760b0cd6a90ab8232194cef7 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1599808.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f777fafa9cc0919950a0231834f75954a17c4e07b9bcf7c6b2b3dbc5426c41 +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1599808.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1599808.pt new file mode 100644 index 0000000000000000000000000000000000000000..5be3d01293808d50c0d08e83f094ad3145a81024 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1599808.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f311e89bfe1d1fa8a578efe91d9ceafece8fa50a349a0721013634ff0e664ef9 +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1699840.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1699840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..9ad7b16ce777304df97990366758cb5b2fff8f55 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1699840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90533537979d9abeb815e499a777474c4c0c66e3068c3e9de39c17512f6cd35c +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1699840.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1699840.pt new file mode 100644 index 0000000000000000000000000000000000000000..f774862b573b9340bd42c6c3d2f9ce599f408198 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1699840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09f5ead3bb039e49e211a2ca8d7afa788223c1ed2b9883342efc46ef66799982 +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1799808.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1799808.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ea11328069ca24a0a116481b4bb2a48e6e77d4d5 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1799808.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de1ea3ba5c8d90ce7be467ee2871441c2dbb220e8761d14b8c3d70439bc9ad7b +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1799808.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1799808.pt new file mode 100644 index 0000000000000000000000000000000000000000..85e5e53e145471ac02295fb002cab589fc757d96 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1799808.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32def0f45b71e638ddd1ad302b620df2526e4099b0bc65c9f4b1ec7a2737b092 +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1899840.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1899840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8076d8d1a8459a9c7a94f8078a6267136d88a327 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1899840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9677e46c8e368b0e5f5a3aa982ca3949bf1f4489fa58ae55cea8801e56563aba +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1899840.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1899840.pt new file mode 100644 index 0000000000000000000000000000000000000000..bf279ced3d4298af0473da7bcf994dad3060230b --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1899840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9cacd7cdf76e019c35c7618a719b7c58d5b468f7a47d136dc4d1dcea7ede6b7 +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1999872.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-1999872.onnx new file mode 100644 index 0000000000000000000000000000000000000000..8f5a845cd19907d34729a4c755e3cb5ccabdaa90 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1999872.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eb6959372271405f646cec449cddcc6d19f604a7d02b5422b02aa7035aa9906 +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-1999872.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-1999872.pt new file mode 100644 index 0000000000000000000000000000000000000000..d26ee217519ba26a0a166f68c6998258c73bd031 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-1999872.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfc7b6a20afe2601acf9523584f01e56a6a62f274dff5066b5b53ae4621953aa +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-2005504.onnx b/results/tau_agent_A1_2M/checkpoints/TauAgent-2005504.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d8c54ebc3ed23996dd2fb8d86eb7e9b4ce665fc3 --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-2005504.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08931e19cffa93c14fed86e9bb88278424715303928d4761bf3dcc257fdde73d +size 2186395 diff --git a/results/tau_agent_A1_2M/checkpoints/TauAgent-2005504.pt b/results/tau_agent_A1_2M/checkpoints/TauAgent-2005504.pt new file mode 100644 index 0000000000000000000000000000000000000000..16c6827f30bb1b84e4587a30d4307dfbdc31028d --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/TauAgent-2005504.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260196c3491aca9156c57f3d29bba9cb40b9655acd53407f09075f191df035ae +size 15534256 diff --git a/results/tau_agent_A1_2M/checkpoints/checkpoint.pt b/results/tau_agent_A1_2M/checkpoints/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..12bdeb8fdd14bd82d9f12f26cfed2c1ea3d8881b --- /dev/null +++ b/results/tau_agent_A1_2M/checkpoints/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37080da1574efbcf39b5938261f36738c44437f2ceb72501058d86a7ffe8d386 +size 15533332 diff --git a/results/tau_agent_A1_2M/configuration.yaml b/results/tau_agent_A1_2M/configuration.yaml new file mode 100644 index 0000000000000000000000000000000000000000..5f9470c8e1a5b42aeb02f6ac8345a6f00e7de338 --- /dev/null +++ b/results/tau_agent_A1_2M/configuration.yaml @@ -0,0 +1,93 @@ +default_settings: null +behaviors: + TauAgent: + trainer_type: ppo + hyperparameters: + batch_size: 256 + buffer_size: 4096 + learning_rate: 3.0e-05 + beta: 0.005 + epsilon: 0.2 + lambd: 0.95 + num_epoch: 7 + shared_critic: false + learning_rate_schedule: linear + beta_schedule: linear + epsilon_schedule: linear + checkpoint_interval: 100000 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: + sequence_length: 256 + memory_size: 256 + goal_conditioning_type: hyper + deterministic: false + reward_signals: + extrinsic: + gamma: 0.99 + strength: 1.0 + network_settings: + normalize: false + hidden_units: 128 + num_layers: 2 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + curiosity: + gamma: 0.995 + strength: 0.1 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + learning_rate: 0.0003 + encoding_size: null + init_path: null + keep_checkpoints: 10 + even_checkpoints: false + max_steps: 2000000 + time_horizon: 256 + summary_freq: 10000 + threaded: true + self_play: null + behavioral_cloning: null +env_settings: + env_path: .\Build + env_args: null + base_port: 5005 + num_envs: 1 + num_areas: 1 + timeout_wait: 300 + seed: -1 + max_lifetime_restarts: 10 + restarts_rate_limit_n: 1 + restarts_rate_limit_period_s: 60 +engine_settings: + width: 84 + height: 84 + quality_level: 5 + time_scale: 20 + target_frame_rate: -1 + capture_frame_rate: 60 + no_graphics: false +environment_parameters: null +checkpoint_settings: + run_id: tau_agent_ppo_A1 + initialize_from: null + load_model: false + resume: false + force: true + train_model: false + inference: false + results_dir: results +torch_settings: + device: cuda +debug: false diff --git a/results/tau_agent_A3_1M/Tau-A3-1M.onnx b/results/tau_agent_A3_1M/Tau-A3-1M.onnx new file mode 100644 index 0000000000000000000000000000000000000000..1a2decf9877ede7c8b3500356ed7bbff530e3296 --- /dev/null +++ b/results/tau_agent_A3_1M/Tau-A3-1M.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5d20133e25c7b1f17c9fe045373f12448adfba0a341d2ce0ab683dc0a505e9 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-1001575.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-1001575.onnx new file mode 100644 index 0000000000000000000000000000000000000000..1a2decf9877ede7c8b3500356ed7bbff530e3296 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-1001575.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5d20133e25c7b1f17c9fe045373f12448adfba0a341d2ce0ab683dc0a505e9 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-1001575.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-1001575.pt new file mode 100644 index 0000000000000000000000000000000000000000..d73cee50e24b658887ba245357f7c6c96fe32bf5 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-1001575.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c1e3f84038d1be138512d0c2b168f8fed07c9e123765c992dbb88ce19ad9729 +size 23269214 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-12324.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-12324.onnx new file mode 100644 index 0000000000000000000000000000000000000000..068e89f5706b65f47a37469cadb65e06b5b553e4 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-12324.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaf958d6b87edcf7ebcfbfe28296a04bbdb8f8a5fad6aa1b8f23bcf747cd89d1 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-12324.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-12324.pt new file mode 100644 index 0000000000000000000000000000000000000000..44639234ebeb466924e49eef99b0cc2cc5e1f4cd --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-12324.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c98eb2737900135b3e52175a3b2c94a6d3bd3c88d1b85667f32af788be5b6075 +size 23268710 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-199903.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-199903.onnx new file mode 100644 index 0000000000000000000000000000000000000000..a3bced039dc6fb39c84e90ed290b9a9cd922055a --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-199903.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f024ccd7748fde0b0b7e8fa59d06951bf15fcefb555457746ee03d2f7a90bbc +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-199903.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-199903.pt new file mode 100644 index 0000000000000000000000000000000000000000..af8e3f4d5ccdbdfcf94c6844c583ef899821c1c5 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-199903.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b77bbf92946f07c4ea7dba982ce78ad57c00ee5a9bca7edd7271d7918bbbda7 +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-28282.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-28282.onnx new file mode 100644 index 0000000000000000000000000000000000000000..eb5318ccf257554b6c9f199edc645bde712d983c --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-28282.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd48d742cff7e006aa71e8dcb2c31c31c74bc9ae03d54b76559c3b3dd8745c61 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-28282.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-28282.pt new file mode 100644 index 0000000000000000000000000000000000000000..388cca179efa58ce3bd355cae00aaf5ff4d005fe --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-28282.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8513da1f1353113fd99c51dd85e61f57e4dfb4b8d31b644d0f7af73ac4c3b47e +size 23268710 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-299879.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-299879.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ab7f768a2881fbdd12d9446ea92dc85c9575b0fb --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-299879.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff77dadbb9a1fafc12a4946bdd5c63f4e6f43fa1763cff4dd0929fa3d499a2b +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-299879.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-299879.pt new file mode 100644 index 0000000000000000000000000000000000000000..7f0cdfe32ad58493134dd1858fbf702be20b7c62 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-299879.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b03039f2bdfbaa4625a6f13b8580c72c43bef5bfd9025e9f915e2bf3a51b8dfa +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-399831.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-399831.onnx new file mode 100644 index 0000000000000000000000000000000000000000..f66468eef3c3d4761e691a14de3ec3269aba41eb --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-399831.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0f215196437e7d6a5e1757fb59a21b4ea1cda1a3b7af937a427659a375b9a0d +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-399831.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-399831.pt new file mode 100644 index 0000000000000000000000000000000000000000..b1311f6118051dcee5575220a7d924d6686616a3 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-399831.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0bd14a4a2ab99d335f034d318f7c372770c62ea615a4e2804bd8994de6b8050 +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-499989.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-499989.onnx new file mode 100644 index 0000000000000000000000000000000000000000..4f6e72197bca4a95af55a2a78595c4a41f5c39b9 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-499989.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:187b76bb76c34cba0dac85f49f58a7ea5bde3e4a23f9bfc899e2023cdbba3e70 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-499989.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-499989.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb5c3e90951f80fa9d2835e98565a9d0df484740 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-499989.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782a3ce94817b5f93f82f245128eabd0e5944a6f1ce158921c7cb500cc53c1d2 +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-599755.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-599755.onnx new file mode 100644 index 0000000000000000000000000000000000000000..b0531a4fea7a0a07a6f0b9d3287cadcff94ce317 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-599755.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:545ee682b7953e6ed53cb351c7e17d16fcd665bf5d9a9f3cb1e32452bceaa760 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-599755.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-599755.pt new file mode 100644 index 0000000000000000000000000000000000000000..fa79f04af26b47536605c992ec02fe8d7884959f --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-599755.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53a8c5e1897e7aa448878fc936a0b0968addbffe7e0b73cfa17999fd75de4aa6 +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-699907.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-699907.onnx new file mode 100644 index 0000000000000000000000000000000000000000..f1368c29fc48f4dff667fbdfc11322e51277376f --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-699907.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5f5612c9190f8d25f0b2e1ae27d72aca029f7962cd1d1c9c2605296389979b4 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-699907.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-699907.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ae929ae8c5ee977760c4d3665462cc4d416be06 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-699907.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01a48a1e97204e86b79e57dde69e65a2e156df2159595e7583f69355a2726e41 +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-799975.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-799975.onnx new file mode 100644 index 0000000000000000000000000000000000000000..6f10fa1342bae3a0b1a6f0df51c712b1841f9021 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-799975.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3946bf8a6a03014256bedd19b4965ec552903ba24a711ac5b3ae5bfd96e18f82 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-799975.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-799975.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ee6bdda2c9b61dc15c36463a1648709921c67c6 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-799975.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50854837ea697627700f4b23582acd5083cbc41be015f5177bec6fa417a75141 +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-899787.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-899787.onnx new file mode 100644 index 0000000000000000000000000000000000000000..755577b64ebaf033bebd85c50ae60c6002e8ad3b --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-899787.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3834f38a6da9d23a037c64da280ad1b87c77d9228ffc461ccc7c312a0f147c38 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-899787.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-899787.pt new file mode 100644 index 0000000000000000000000000000000000000000..55abdc9de6cf747927225c0c2cda3490dfc8d82a --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-899787.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c4867e2a04b63b7412b26745df14b83b2a4465dfcd36b37018158fa2b685661 +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-999987.onnx b/results/tau_agent_A3_1M/checkpoints/TauAgent-999987.onnx new file mode 100644 index 0000000000000000000000000000000000000000..75bb597ddc5d11b3b3ef52e6079b12ff0a2e36c3 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-999987.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f599e796aa05601ba2a7a5c54f4c702594601fa5c5d3861f60964129a4d4109 +size 1983173 diff --git a/results/tau_agent_A3_1M/checkpoints/TauAgent-999987.pt b/results/tau_agent_A3_1M/checkpoints/TauAgent-999987.pt new file mode 100644 index 0000000000000000000000000000000000000000..6a9de108b68cecc148bff046f00a17c5d9f86a18 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/TauAgent-999987.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d7607c7b79859970d0162c13f77a89730ac548341ae0438001612c2ab0745ab +size 23268962 diff --git a/results/tau_agent_A3_1M/checkpoints/checkpoint.pt b/results/tau_agent_A3_1M/checkpoints/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..28638313fa84cf4d15f58add6b7bcc9d29998914 --- /dev/null +++ b/results/tau_agent_A3_1M/checkpoints/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94b764243f51b496724081db5f3d7a11d270dc706ec1c5635abfc81dc20cfb0b +size 23267702 diff --git a/results/tau_agent_A3_1M/configuration.yaml b/results/tau_agent_A3_1M/configuration.yaml new file mode 100644 index 0000000000000000000000000000000000000000..43814919cdad01d5825c708ea5c419e059147fb3 --- /dev/null +++ b/results/tau_agent_A3_1M/configuration.yaml @@ -0,0 +1,90 @@ +default_settings: null +behaviors: + TauAgent: + trainer_type: sac + hyperparameters: + learning_rate: 3.0e-05 + learning_rate_schedule: linear + batch_size: 256 + buffer_size: 100000 + buffer_init_steps: 0 + tau: 0.005 + steps_per_update: 30.0 + save_replay_buffer: false + init_entcoef: 0.01 + reward_signal_steps_per_update: 30.0 + checkpoint_interval: 100000 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + reward_signals: + extrinsic: + gamma: 0.99 + strength: 1.0 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + curiosity: + gamma: 0.995 + strength: 0.1 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + learning_rate: 0.0003 + encoding_size: null + init_path: null + keep_checkpoints: 10 + even_checkpoints: false + max_steps: 1000000 + time_horizon: 256 + summary_freq: 10000 + threaded: true + self_play: null + behavioral_cloning: null +env_settings: + env_path: .\Build + env_args: null + base_port: 5005 + num_envs: 1 + num_areas: 1 + timeout_wait: 300 + seed: -1 + max_lifetime_restarts: 10 + restarts_rate_limit_n: 1 + restarts_rate_limit_period_s: 60 +engine_settings: + width: 84 + height: 84 + quality_level: 5 + time_scale: 20 + target_frame_rate: -1 + capture_frame_rate: 60 + no_graphics: false +environment_parameters: null +checkpoint_settings: + run_id: tau_agent_sac_A3 + initialize_from: null + load_model: false + resume: false + force: true + train_model: false + inference: false + results_dir: results +torch_settings: + device: cuda +debug: false diff --git a/results/tau_agent_A4_1M/Tau-A4-1M.onnx b/results/tau_agent_A4_1M/Tau-A4-1M.onnx new file mode 100644 index 0000000000000000000000000000000000000000..4b4d32a76b5f9ded68512e55dce0c5ea9a7ddfe6 --- /dev/null +++ b/results/tau_agent_A4_1M/Tau-A4-1M.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfdf916e4f6b03d72c9c04ac6882596b74141e791bf60c5102952853b9725ac0 +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-1010432.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-1010432.onnx new file mode 100644 index 0000000000000000000000000000000000000000..4b4d32a76b5f9ded68512e55dce0c5ea9a7ddfe6 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-1010432.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfdf916e4f6b03d72c9c04ac6882596b74141e791bf60c5102952853b9725ac0 +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-1010432.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-1010432.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1f9130e8ad48716f778b6ccfce0751afd0bf067 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-1010432.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30e7e7a005c967190d7ba8ba6c0fb7dad2fb85bb6cae28b86e10d5a1c8347c7b +size 11375354 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-199808.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-199808.onnx new file mode 100644 index 0000000000000000000000000000000000000000..6451ded9808413e1cd8fe38747eabc2176eabb33 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-199808.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85da9333d7847aec4fe22fc3395428cbb151ef4e3b1ddc4d5841a7b234038b20 +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-199808.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-199808.pt new file mode 100644 index 0000000000000000000000000000000000000000..87e0573bdceb50d8e3c611e76dee71184263ac55 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-199808.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a96d2b8ee290cde90ad1670b2e5dbcbd35068bf642c44cfd05f1b30570157acc +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-299840.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-299840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..4deb251201e6356993eb5be85b68764668df619a --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-299840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0361018cad5c3f4930e18260830fe874219509da5ac22adae98b556021bc62 +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-299840.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-299840.pt new file mode 100644 index 0000000000000000000000000000000000000000..c14fd061d9e50d1e0c10c3f300c46eaedf0f95de --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-299840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784a13a1a4455d7ef3f939fef3864d38dc111dcf47e5b116c863d045b7bd0dce +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-399964.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-399964.onnx new file mode 100644 index 0000000000000000000000000000000000000000..6fe12a1f57fd26a07e537a9329401f3eea47d2ab --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-399964.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cc66797536890ba77b3fd570f58bf110205b26ac2f6d4b92a51bebd901f6185 +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-399964.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-399964.pt new file mode 100644 index 0000000000000000000000000000000000000000..2729017ede5961deea4aa8631c8b67fbb396a01b --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-399964.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44b7b73ff1141b0c23e932fb2fe9aceac9cac90b80046b37e73959d1cbd99ccd +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-499840.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-499840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ed5949efe6540ab6a400fd71fe35c61b46a700ca --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-499840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222e111ff3adcf9283f1fd559c40e98a8743676dbc73cd327ccc309e0b43aeda +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-499840.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-499840.pt new file mode 100644 index 0000000000000000000000000000000000000000..a6a2756fdd7cd94a3e23e31979842ff29291b0c8 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-499840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad3be59ae27a1f186c4ebe43ad7449cab2206a7d5cffbc006bdc9b9941e6e90 +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-599872.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-599872.onnx new file mode 100644 index 0000000000000000000000000000000000000000..872b4d2deda20ec6d9a11d3cf58990effdbdcc36 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-599872.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5244afa1269fd932e1622da8d10ce3fd2637ee1a7134ee20b3544ba7f9b7c2b +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-599872.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-599872.pt new file mode 100644 index 0000000000000000000000000000000000000000..e1d20ccd9f0b4f8f6f473ff6525d7b5bec509344 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-599872.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9be12038767dfc1ec570089c476f5f2f35c8b4af6f7d6c765d96175434f88449 +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-699904.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-699904.onnx new file mode 100644 index 0000000000000000000000000000000000000000..b73e13a8ee8ffb464427e74d05b68152ad22cfc0 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-699904.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4535ff01f1e8d82002e40379b33368be0dfa67866a51f87c5aa7ae4825060e9c +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-699904.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-699904.pt new file mode 100644 index 0000000000000000000000000000000000000000..65aa285b1460473cce543f575230fd2461f5bfd0 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-699904.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1936876e9976dcce94f47c8d12460592d931d7463ef23281407312a69908d7b +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-799936.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-799936.onnx new file mode 100644 index 0000000000000000000000000000000000000000..001ec8e7204666518f0813ed515981613df0f430 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-799936.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ad9662de78fe945bb536cd130b7865d4dd1fdddb8cdcf9c7eb1014a4247b18 +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-799936.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-799936.pt new file mode 100644 index 0000000000000000000000000000000000000000..390d6ad60bcb25e7973291e042bb0acc0845e393 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-799936.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6479a83787dff2cd1a4868a680fd7a3f804a1ef2894a9efbe683bc7e073c279d +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-899904.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-899904.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3f093b6d8fa41e8ab822e1de56459df663d85d86 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-899904.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebd3812e2dd581ef3b82133283310663bbd3596cda2951a1609677c3170bad48 +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-899904.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-899904.pt new file mode 100644 index 0000000000000000000000000000000000000000..60ea9eff6e828e2a5d8adc605c274dc0d577e5dc --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-899904.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb6cda34b6cd88d6544d16fbc3a610b51e04db0b7b001d12838fcbd6b27589e0 +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-999936.onnx b/results/tau_agent_A4_1M/checkpoints/TauAgent-999936.onnx new file mode 100644 index 0000000000000000000000000000000000000000..68e6a208329e40dc1abb5d6544eea3b2b14fce67 --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-999936.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdce2453fcdfec7b29dbe06779de0111dd31223404ba5efcdb88ec4cdb3dd007 +size 1590263 diff --git a/results/tau_agent_A4_1M/checkpoints/TauAgent-999936.pt b/results/tau_agent_A4_1M/checkpoints/TauAgent-999936.pt new file mode 100644 index 0000000000000000000000000000000000000000..d6324f6eacf253f37f0a05aa653c607d08606ccd --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/TauAgent-999936.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fb23c658e565021c389b69a3511e22dbff6146e4fd4f5eb73ae59d8f628b9ea +size 11375226 diff --git a/results/tau_agent_A4_1M/checkpoints/checkpoint.pt b/results/tau_agent_A4_1M/checkpoints/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..34d1e7b5fcbd5cf6522256d02e850fd282e6efbd --- /dev/null +++ b/results/tau_agent_A4_1M/checkpoints/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449957b3560e3a1a24b287932e799599a4610a4c065fbcdde862863ca7b400f4 +size 11374586 diff --git a/results/tau_agent_A4_1M/configuration.yaml b/results/tau_agent_A4_1M/configuration.yaml new file mode 100644 index 0000000000000000000000000000000000000000..e6e394f20d53fbfdabe37542994d6279765d2813 --- /dev/null +++ b/results/tau_agent_A4_1M/configuration.yaml @@ -0,0 +1,91 @@ +default_settings: null +behaviors: + TauAgent: + trainer_type: ppo + hyperparameters: + batch_size: 256 + buffer_size: 4096 + learning_rate: 3.0e-05 + beta: 0.005 + epsilon: 0.2 + lambd: 0.95 + num_epoch: 3 + shared_critic: false + learning_rate_schedule: linear + beta_schedule: linear + epsilon_schedule: linear + checkpoint_interval: 100000 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + reward_signals: + extrinsic: + gamma: 0.99 + strength: 1.0 + network_settings: + normalize: false + hidden_units: 128 + num_layers: 2 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + curiosity: + gamma: 0.995 + strength: 0.1 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + learning_rate: 0.0003 + encoding_size: null + init_path: null + keep_checkpoints: 10 + even_checkpoints: false + max_steps: 1000000 + time_horizon: 256 + summary_freq: 10000 + threaded: true + self_play: null + behavioral_cloning: null +env_settings: + env_path: .\Build + env_args: null + base_port: 5005 + num_envs: 1 + num_areas: 1 + timeout_wait: 300 + seed: -1 + max_lifetime_restarts: 10 + restarts_rate_limit_n: 1 + restarts_rate_limit_period_s: 60 +engine_settings: + width: 84 + height: 84 + quality_level: 5 + time_scale: 20 + target_frame_rate: -1 + capture_frame_rate: 60 + no_graphics: false +environment_parameters: null +checkpoint_settings: + run_id: tau_agent_sac_A4 + initialize_from: null + load_model: false + resume: false + force: true + train_model: false + inference: false + results_dir: results +torch_settings: + device: cuda +debug: false diff --git a/results/tau_agent_A5_1M/Tau-A5-1M.onnx b/results/tau_agent_A5_1M/Tau-A5-1M.onnx new file mode 100644 index 0000000000000000000000000000000000000000..35ab73c2a4bd5cf5f788dadd87db2a4e1af1e6fb --- /dev/null +++ b/results/tau_agent_A5_1M/Tau-A5-1M.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03dd23f09db5db4c348d691eae0e6a8933ed601ea5b9dd9acb11bf1e181811e8 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-1010432.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-1010432.onnx new file mode 100644 index 0000000000000000000000000000000000000000..35ab73c2a4bd5cf5f788dadd87db2a4e1af1e6fb --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-1010432.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03dd23f09db5db4c348d691eae0e6a8933ed601ea5b9dd9acb11bf1e181811e8 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-1010432.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-1010432.pt new file mode 100644 index 0000000000000000000000000000000000000000..652823df65787f247d6f0f04c2b1bad43dd1c301 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-1010432.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85f7e923a58773a7d2b8281d2f5085ce6726b5efe19822288429fc33e638cadb +size 11375354 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-199808.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-199808.onnx new file mode 100644 index 0000000000000000000000000000000000000000..570c2da8338e499a27c92202882a1d57b5a05238 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-199808.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b249b24bba6a83a1cb6e2ed39e2272945e9ad894592dfb1d38f6990932db7e53 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-199808.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-199808.pt new file mode 100644 index 0000000000000000000000000000000000000000..b0f11c0a4410936b8b9d0939e35b465cc11d6c55 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-199808.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd2f9e6e5580f7f69801d93f8c07c28b1ee7e9b7d4425acbb7f01bca022a2fb +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-299840.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-299840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..be4f24f5d59fc3457260899806cc5f4bc81e5e95 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-299840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26cb471d7b43d2802ebef24fde91f697204b3d9eaff6621cee412140fcc4bc1c +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-299840.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-299840.pt new file mode 100644 index 0000000000000000000000000000000000000000..bc352b863e4921f291b86273c2db76f1c0261eff --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-299840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2cb1490c8f70433030797ec143aa4eafe2419b331797511828db8d03eb23f3a +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-399964.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-399964.onnx new file mode 100644 index 0000000000000000000000000000000000000000..ccc87e4948c2b591e4a35bd62442e061874d0212 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-399964.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7eecae8ceea57df8923e1d750e03fed4f24efa7f0ab2e561fbc712c657f043 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-399964.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-399964.pt new file mode 100644 index 0000000000000000000000000000000000000000..4d3cd1ad81b35ff05461a93c43b7cfbdda79d824 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-399964.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c38c3552b424d154d879bdbe163c7dee9e6abcca7ba86bb66d391a068ecad71 +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-499840.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-499840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..de5f8f11a55b2d95871cc1f422ea7b70e623f3ee --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-499840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f217f360540c274da70d2031756abfee9b5354fcffc99d12c6ab70612c59580 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-499840.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-499840.pt new file mode 100644 index 0000000000000000000000000000000000000000..0a36c83e81466c0fbbb6c53913280271d6847658 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-499840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e887ea3226dd4dbaf1c02c4ae16ad60c8c96fb24836c6d8920380c0bd2c34e85 +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-599872.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-599872.onnx new file mode 100644 index 0000000000000000000000000000000000000000..909c4c72150e93342d3e87ab416612483324347b --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-599872.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3198ac9c3c10ca63d85f8c0d09f7435724a4bfe2bb8fd7431cdf0d6eb05898 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-599872.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-599872.pt new file mode 100644 index 0000000000000000000000000000000000000000..054f3dee3e2f5285fa16fc7949195c20c2de8f44 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-599872.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1f0de731582c0519f5a770f3742258f4e95c3cc0135e4749021fa2808152ea4 +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-699904.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-699904.onnx new file mode 100644 index 0000000000000000000000000000000000000000..c9ccc8ceeaaf22777e170bf86dcf6e9c7b5ac326 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-699904.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ab04db01f394b616edd897cec67bf5aa8ea23d76b008693d6d4ef1f63f87102 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-699904.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-699904.pt new file mode 100644 index 0000000000000000000000000000000000000000..b05b16b301cf99e9e8b9fc9c18036d6891078b4f --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-699904.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a508200fce2bae65dd9ba8bd8c40c4bc1ae1c81219068ce131e4d10427661770 +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-799936.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-799936.onnx new file mode 100644 index 0000000000000000000000000000000000000000..91f5327585e18506d9e43f44c9cd7e5fac3bf28b --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-799936.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8d422cd899dcf90d744470df36201e3efc497d41a8dcda1a032f942c1c2bb6b +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-799936.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-799936.pt new file mode 100644 index 0000000000000000000000000000000000000000..7fa19705141d2c466534701345950e9deeca35e7 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-799936.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a3147b519e4ee281668a27f5207f57073f2632dab9720e064d46dff7b0636e4 +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-899904.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-899904.onnx new file mode 100644 index 0000000000000000000000000000000000000000..27221fc12e4766491efc07e5f49770b82c638528 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-899904.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d0a39b9a4dd983d0144dd73356c307700362ee116cc2c9d6c5244cb8578564 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-899904.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-899904.pt new file mode 100644 index 0000000000000000000000000000000000000000..6ecdac3bb3f22b510349c68b1372be6ca106e423 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-899904.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef7f13037e2093727d7c29467eb121d2a909ca085eb0510c83d867fdc7f1743d +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-999936.onnx b/results/tau_agent_A5_1M/checkpoints/TauAgent-999936.onnx new file mode 100644 index 0000000000000000000000000000000000000000..26911b29d1bbda6d8aaa45f0bfafbddad49b0277 --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-999936.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c92677fa36b0fe9477281b9da54c9f93dec1cdf501e7c2c9f12d5be36d4ead11 +size 1590263 diff --git a/results/tau_agent_A5_1M/checkpoints/TauAgent-999936.pt b/results/tau_agent_A5_1M/checkpoints/TauAgent-999936.pt new file mode 100644 index 0000000000000000000000000000000000000000..555a3d1935cc287af22ee1f65c5774d635496a4a --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/TauAgent-999936.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d566611bb3f48603008142c5e30fe36211c2a5fbfee309a6beb0b6ed8c59574c +size 11375226 diff --git a/results/tau_agent_A5_1M/checkpoints/checkpoint.pt b/results/tau_agent_A5_1M/checkpoints/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..71dc47d42e32770f1ac70f1c3695acdc3d7ac6fe --- /dev/null +++ b/results/tau_agent_A5_1M/checkpoints/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a19ed3e58514e3a520de16eb2817a85b15bb5e0d34485d2496b5850bbf9cec8 +size 11374586 diff --git a/results/tau_agent_A5_1M/configuration.yaml b/results/tau_agent_A5_1M/configuration.yaml new file mode 100644 index 0000000000000000000000000000000000000000..1c6a6cea1324eb4ea9a35f8c898adfb3ce68678f --- /dev/null +++ b/results/tau_agent_A5_1M/configuration.yaml @@ -0,0 +1,91 @@ +default_settings: null +behaviors: + TauAgent: + trainer_type: ppo + hyperparameters: + batch_size: 256 + buffer_size: 4096 + learning_rate: 3.0e-05 + beta: 0.005 + epsilon: 0.2 + lambd: 0.95 + num_epoch: 3 + shared_critic: false + learning_rate_schedule: linear + beta_schedule: linear + epsilon_schedule: linear + checkpoint_interval: 100000 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + reward_signals: + extrinsic: + gamma: 0.99 + strength: 1.0 + network_settings: + normalize: false + hidden_units: 128 + num_layers: 2 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + curiosity: + gamma: 0.995 + strength: 0.1 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + learning_rate: 0.0003 + encoding_size: null + init_path: null + keep_checkpoints: 10 + even_checkpoints: false + max_steps: 1000000 + time_horizon: 256 + summary_freq: 10000 + threaded: true + self_play: null + behavioral_cloning: null +env_settings: + env_path: .\Build + env_args: null + base_port: 5005 + num_envs: 1 + num_areas: 1 + timeout_wait: 300 + seed: -1 + max_lifetime_restarts: 10 + restarts_rate_limit_n: 1 + restarts_rate_limit_period_s: 60 +engine_settings: + width: 84 + height: 84 + quality_level: 5 + time_scale: 20 + target_frame_rate: -1 + capture_frame_rate: 60 + no_graphics: false +environment_parameters: null +checkpoint_settings: + run_id: tau_agent_sac_A5 + initialize_from: null + load_model: false + resume: false + force: true + train_model: false + inference: false + results_dir: results +torch_settings: + device: cuda +debug: false diff --git a/results/tau_agent_A6_1M/Tau-A6-1M.onnx b/results/tau_agent_A6_1M/Tau-A6-1M.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3bf09eb4e411a0bcf5988db65414bf11d309d31a --- /dev/null +++ b/results/tau_agent_A6_1M/Tau-A6-1M.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9696cc66d58dd113d1b2acbbcac19ff67dcddba2cc333738d03d93c1719ee66a +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-1013012.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-1013012.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3bf09eb4e411a0bcf5988db65414bf11d309d31a --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-1013012.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9696cc66d58dd113d1b2acbbcac19ff67dcddba2cc333738d03d93c1719ee66a +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-1013012.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-1013012.pt new file mode 100644 index 0000000000000000000000000000000000000000..c2a14378b5078f376736da70c250ab06ed3f8da3 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-1013012.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ac59936cdc894a4a91fc5c90697fae7db3cf049e641f9b12e88691b8566dcfa +size 11375354 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-199732.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-199732.onnx new file mode 100644 index 0000000000000000000000000000000000000000..1f0133d6f9eece8e4c92fd4ad1dc4b98721daf83 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-199732.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f44251d063ba0e9704ebc567281fb031a0ac6502d0a113faefad842b7e335a +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-199732.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-199732.pt new file mode 100644 index 0000000000000000000000000000000000000000..21fee847a66e8532510f41b2448c1b816b5c5e68 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-199732.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e38f8a389bccba894c656249c538499d5eb29d056635b22664ecb9441824acdb +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-299897.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-299897.onnx new file mode 100644 index 0000000000000000000000000000000000000000..c376ae2d79ba00a51c4ec0da116d107f3d123cd2 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-299897.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcf5d1553131f211ccea2f5d59a68d15c136e12d26ddd72688944104edf8dc3e +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-299897.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-299897.pt new file mode 100644 index 0000000000000000000000000000000000000000..7e4d9e9910400e8c02005e91dc3204a8e4bc7359 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-299897.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281a1e319da64cf8deb28f3a66fe9d6d5632235c61ba3fff6162cb1759544435 +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-399763.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-399763.onnx new file mode 100644 index 0000000000000000000000000000000000000000..40c7b6af770516b10c7d52fd9226b4a6ba716bb5 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-399763.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b1c9af5d79e0b43ded764c070be088075f48051b967728175ab3f35c8b336fe +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-399763.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-399763.pt new file mode 100644 index 0000000000000000000000000000000000000000..984e15208f458bc93b73da215a57f8d7b0a17f26 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-399763.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5feadd1f0fb0642c9fec335c7cacdb7d82d64f94359555bbe95ae070b9455749 +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-499928.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-499928.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0221117a5c3992ef406524d972c45c4e44ef606e --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-499928.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae2c41b8c0b6f4c702cd8cac9efcbae91692d75de34072212709495df0e6100 +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-499928.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-499928.pt new file mode 100644 index 0000000000000000000000000000000000000000..f7251b64756299a640e06aafadb159d429dc9a78 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-499928.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804456a6ac2bd3b50ad2eacfe669b98b886be3517d8ebfb40ff85ebd09bc992d +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-599794.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-599794.onnx new file mode 100644 index 0000000000000000000000000000000000000000..0112a1ce4a3e994110e6a32742982ad67ebffb4f --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-599794.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e8139d1e5a00b306dd3330d7065b03e886b8307b36a0474c1c28399093687e6 +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-599794.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-599794.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca3131d0fcc22e15c2f315c6fab997368aa83eac --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-599794.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1afb1d1c0d6e071c318a2c44949067d84f0f59f534f9ccc3a6ac51da6cda1b16 +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-699959.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-699959.onnx new file mode 100644 index 0000000000000000000000000000000000000000..cab926b02717a4c172c8a5a4ca207ed277c8ed4d --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-699959.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89a5796d6439690d3fafcd1ddab6d1554350c5af7a3e82ec6d7ee215cbc9fcd3 +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-699959.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-699959.pt new file mode 100644 index 0000000000000000000000000000000000000000..0e04e9539d5f9708e842c5d2889149809230e80d --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-699959.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6bf913ca2084540c3ed62164fb5e7b4db12a16c6d718ece60fed85942385f92 +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-799825.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-799825.onnx new file mode 100644 index 0000000000000000000000000000000000000000..065eb3862f4f00b3913a4990162ff37365847684 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-799825.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e8e5324d36f038e786de17c3c35c9865e62d7e2211a1231715b483d3f47b5d +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-799825.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-799825.pt new file mode 100644 index 0000000000000000000000000000000000000000..700544d00f387e345a7ac02f887b1984515d2d31 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-799825.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc17c1b90aeaebd683bf0d7e58ca0dbbe875b788662e4cd51eebe49647a23a5b +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-899990.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-899990.onnx new file mode 100644 index 0000000000000000000000000000000000000000..66ac5cfe62698dc258a827393505ce2702ea3304 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-899990.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6106f0378198121629d29e75b89a7a9be72905d0544b8b0890564d82eb34a5a +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-899990.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-899990.pt new file mode 100644 index 0000000000000000000000000000000000000000..7ec63c7ef4a3b214bd47c6e26f48af5b2881f802 --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-899990.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a3d6e44cc937ce2920e7f4049dad404e76262b9102c3f48cb6c112243f0e205 +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-999856.onnx b/results/tau_agent_A6_1M/checkpoints/TauAgent-999856.onnx new file mode 100644 index 0000000000000000000000000000000000000000..22e7abb530f40d10d227259221ed1e9ce4cc8aaf --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-999856.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4315352728510ff2c16fef1cb89491336c69a5720a47da5799ff92a79788d60a +size 1590263 diff --git a/results/tau_agent_A6_1M/checkpoints/TauAgent-999856.pt b/results/tau_agent_A6_1M/checkpoints/TauAgent-999856.pt new file mode 100644 index 0000000000000000000000000000000000000000..9add72ece7ff0ee522e6f7e2bf60cb971915d4ad --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/TauAgent-999856.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb4bc051404189ee4a66bb7029ddc65bf90483c2f033dcfb83027057697a81f +size 11375226 diff --git a/results/tau_agent_A6_1M/checkpoints/checkpoint.pt b/results/tau_agent_A6_1M/checkpoints/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..19be1b321a86f1f5e75d7e7ba5c6965682ed761c --- /dev/null +++ b/results/tau_agent_A6_1M/checkpoints/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee16c4ab16a88b31a607a24a65af41a798c13d77dd63ef10cce7d5270e74fd3 +size 11374586 diff --git a/results/tau_agent_A6_1M/configuration.yaml b/results/tau_agent_A6_1M/configuration.yaml new file mode 100644 index 0000000000000000000000000000000000000000..ccda3619e7fa9caa91ee3f0ce3676b3b3d6a2e22 --- /dev/null +++ b/results/tau_agent_A6_1M/configuration.yaml @@ -0,0 +1,91 @@ +default_settings: null +behaviors: + TauAgent: + trainer_type: ppo + hyperparameters: + batch_size: 1000 + buffer_size: 4096 + learning_rate: 3.0e-05 + beta: 0.005 + epsilon: 0.2 + lambd: 0.95 + num_epoch: 10 + shared_critic: false + learning_rate_schedule: linear + beta_schedule: linear + epsilon_schedule: linear + checkpoint_interval: 100000 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + reward_signals: + extrinsic: + gamma: 0.99 + strength: 1.0 + network_settings: + normalize: false + hidden_units: 128 + num_layers: 2 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + curiosity: + gamma: 0.995 + strength: 0.1 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + learning_rate: 0.0003 + encoding_size: null + init_path: null + keep_checkpoints: 10 + even_checkpoints: false + max_steps: 1000000 + time_horizon: 1000 + summary_freq: 10000 + threaded: true + self_play: null + behavioral_cloning: null +env_settings: + env_path: .\Build + env_args: null + base_port: 5005 + num_envs: 1 + num_areas: 1 + timeout_wait: 300 + seed: -1 + max_lifetime_restarts: 10 + restarts_rate_limit_n: 1 + restarts_rate_limit_period_s: 60 +engine_settings: + width: 84 + height: 84 + quality_level: 5 + time_scale: 20 + target_frame_rate: -1 + capture_frame_rate: 60 + no_graphics: false +environment_parameters: null +checkpoint_settings: + run_id: tau_agent_sac_A6 + initialize_from: null + load_model: false + resume: false + force: true + train_model: false + inference: false + results_dir: results +torch_settings: + device: cuda +debug: false diff --git a/results/tau_agent_A7_1M/Tau-A7-1M.onnx b/results/tau_agent_A7_1M/Tau-A7-1M.onnx new file mode 100644 index 0000000000000000000000000000000000000000..4bf147a71b2f97131cad22884dfa95af262e5199 --- /dev/null +++ b/results/tau_agent_A7_1M/Tau-A7-1M.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d654e77681c938a82914e5aac9ca08af1680f975f100613cf990e450699a3485 +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-1010432.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-1010432.onnx new file mode 100644 index 0000000000000000000000000000000000000000..4bf147a71b2f97131cad22884dfa95af262e5199 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-1010432.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d654e77681c938a82914e5aac9ca08af1680f975f100613cf990e450699a3485 +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-1010432.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-1010432.pt new file mode 100644 index 0000000000000000000000000000000000000000..273540df68afc5408397049329341e41d8f811af --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-1010432.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5131fae2ed0903620b02a06bfc39801b4f6537a9eb7fc942b98972d40ab013e4 +size 15534256 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-199808.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-199808.onnx new file mode 100644 index 0000000000000000000000000000000000000000..42e1a38a7d2116f847ddce7abacf167553a0f1ea --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-199808.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8521c6e813bbe39324858c0f47b8b57b5b38e36f20b466b4cce5052eae5d7038 +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-199808.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-199808.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ef894018875f33c6ba37868d27423aa74d31405 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-199808.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750e1a722de25b55f2cbe259cc8b032636a5d26a8a88accfe82c818da41d1e63 +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-299840.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-299840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..a5bf1e44709990c3354d3a77a8ff529d9a626d94 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-299840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02eb83b2d379893cfa8e2f7660c37c270a8e2f903eabfcdd8bda177428b34e5 +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-299840.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-299840.pt new file mode 100644 index 0000000000000000000000000000000000000000..b57a6a6474e8da955ff8dd06ce1c02b72837acfb --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-299840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b6f3c961bc33ad88e1c271ad3a376e7a62e6627b17c9369c146dd708e1e67f8 +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-399964.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-399964.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3c0f9a42041aacf06d1ef8eb64babb97b4ce9eca --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-399964.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef5359788896a32357737fff52295e82f70be3054da5403dac05403c673bbae +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-399964.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-399964.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ec16ecd685859fe41a4a82c798c444678dcd7c6 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-399964.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c109476da2db6741c9a4cb3a85f0478953d21316863820a9568ccad3025d199a +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-499840.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-499840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..6cb4410ee4eed26b5d0b58b0cd58d266db4ab20c --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-499840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c78f06a4272bf04b019dd80c5f6186bce097da6337bf15da22cd1e54545e3d +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-499840.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-499840.pt new file mode 100644 index 0000000000000000000000000000000000000000..73512dfce2e08125a0d5159214fc4d219bf44217 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-499840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0665a092ead390888e14a24d3cfc2e5dcc2b97c78ce7a001c6f25678267724 +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-599872.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-599872.onnx new file mode 100644 index 0000000000000000000000000000000000000000..27086ce7561628ec9e745275613428cb9234dff8 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-599872.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:623f5cd789e3277ed3b1fa330507b51a0e7a2f85aa00e097ed1089f425a571c5 +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-599872.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-599872.pt new file mode 100644 index 0000000000000000000000000000000000000000..5b8362eb2b204d7209aa616edf9f34fdaaeae5ad --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-599872.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1a8007d54d782d00570e1430b64784752c0fc8f6d48c2f4c2392e28bf54762 +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-699904.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-699904.onnx new file mode 100644 index 0000000000000000000000000000000000000000..5706da14771eba44757cb7e21d5d7a4acec2305e --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-699904.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db3f4b2a37bb619862dbfd17346ae8739b15d0d80b1f43e6ebd6b6bc745ac37b +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-699904.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-699904.pt new file mode 100644 index 0000000000000000000000000000000000000000..075efc6243e6dc551107886290bd125868c17379 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-699904.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6207341c443cec76f32354be4cc4306c79ed97f061a0c9229d3aaa4abe19d479 +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-799936.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-799936.onnx new file mode 100644 index 0000000000000000000000000000000000000000..d0cca0114d0c647ec4e50d681a9d52f5ba8b3538 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-799936.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dd2c912f8d8220a3149409c47b21a8675ea59bc25d3c8924ad3114d9f1b6712 +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-799936.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-799936.pt new file mode 100644 index 0000000000000000000000000000000000000000..a030ecf498a9d049b874299e7f482f8067039491 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-799936.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b47d072c9f9097edd1b55a4aaa281b6fa6e4100ea604721d8b9a909164b8d6ed +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-899904.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-899904.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3bff930c17d1b196bbcda74f70391b188cf38d59 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-899904.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206fb96e71c1491a7a08908e134d8138f631af69da10d82e05f1b4e9d249a99b +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-899904.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-899904.pt new file mode 100644 index 0000000000000000000000000000000000000000..32df144589abefec6caea7502300ded9733b13ee --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-899904.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:405fc0a0da8c8719ef155d7113b4099e40cf9c712fa861ad45d2c2be42bea944 +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-999936.onnx b/results/tau_agent_A7_1M/checkpoints/TauAgent-999936.onnx new file mode 100644 index 0000000000000000000000000000000000000000..103bf4220a95b3f33d2fa913255873b76c53fe0f --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-999936.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0369bec2111c44f9789066037ec97f85b2b8ec4e8b2007cc22cc93dbc317143 +size 2186395 diff --git a/results/tau_agent_A7_1M/checkpoints/TauAgent-999936.pt b/results/tau_agent_A7_1M/checkpoints/TauAgent-999936.pt new file mode 100644 index 0000000000000000000000000000000000000000..03df8065ce921ede1a8116b8e8adf72f07403547 --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/TauAgent-999936.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc0a2dd1cea5d826cadc2a5b72304f8fe1797365add6aab10e7c3366266bf870 +size 15534102 diff --git a/results/tau_agent_A7_1M/checkpoints/checkpoint.pt b/results/tau_agent_A7_1M/checkpoints/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..52d27f80d94c9533f3f644c8e161f03cb9b69f8b --- /dev/null +++ b/results/tau_agent_A7_1M/checkpoints/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc5f09b77621e66a9f1324ee41c34ed99ebd18109e3d1aa6b088d716c4a1c875 +size 15533332 diff --git a/results/tau_agent_A7_1M/configuration.yaml b/results/tau_agent_A7_1M/configuration.yaml new file mode 100644 index 0000000000000000000000000000000000000000..454676827ab135136ff3d5573d8266b769abc01e --- /dev/null +++ b/results/tau_agent_A7_1M/configuration.yaml @@ -0,0 +1,93 @@ +default_settings: null +behaviors: + TauAgent: + trainer_type: ppo + hyperparameters: + batch_size: 256 + buffer_size: 4096 + learning_rate: 3.0e-05 + beta: 0.005 + epsilon: 0.2 + lambd: 0.95 + num_epoch: 6 + shared_critic: false + learning_rate_schedule: linear + beta_schedule: linear + epsilon_schedule: linear + checkpoint_interval: 100000 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: + sequence_length: 256 + memory_size: 256 + goal_conditioning_type: hyper + deterministic: false + reward_signals: + extrinsic: + gamma: 0.99 + strength: 1.0 + network_settings: + normalize: false + hidden_units: 128 + num_layers: 2 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + curiosity: + gamma: 0.995 + strength: 0.1 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + learning_rate: 0.0003 + encoding_size: null + init_path: null + keep_checkpoints: 10 + even_checkpoints: false + max_steps: 1000000 + time_horizon: 256 + summary_freq: 10000 + threaded: true + self_play: null + behavioral_cloning: null +env_settings: + env_path: .\Build + env_args: null + base_port: 5005 + num_envs: 1 + num_areas: 1 + timeout_wait: 300 + seed: -1 + max_lifetime_restarts: 10 + restarts_rate_limit_n: 1 + restarts_rate_limit_period_s: 60 +engine_settings: + width: 84 + height: 84 + quality_level: 5 + time_scale: 20 + target_frame_rate: -1 + capture_frame_rate: 60 + no_graphics: false +environment_parameters: null +checkpoint_settings: + run_id: tau_agent_sac_A7 + initialize_from: null + load_model: false + resume: false + force: true + train_model: false + inference: false + results_dir: results +torch_settings: + device: cuda +debug: false diff --git a/results/tau_agent_A8_1M/Tau-A8-1M.onnx b/results/tau_agent_A8_1M/Tau-A8-1M.onnx new file mode 100644 index 0000000000000000000000000000000000000000..13c43c3d4b942a5d0cf4cb634ba3646a95db8f67 --- /dev/null +++ b/results/tau_agent_A8_1M/Tau-A8-1M.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c49902904108e92752daba4dcee8b0694ac820df8d1cabc8de2dc64397b919c +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-1010432.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-1010432.onnx new file mode 100644 index 0000000000000000000000000000000000000000..13c43c3d4b942a5d0cf4cb634ba3646a95db8f67 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-1010432.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c49902904108e92752daba4dcee8b0694ac820df8d1cabc8de2dc64397b919c +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-1010432.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-1010432.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb9b58973f7d7cced0ca563ffd5d18e7196ad4d2 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-1010432.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918c795e43d11ea313ca3c9178984c680f86b2d6d4e6f1989427962360f53b47 +size 15534256 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-199808.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-199808.onnx new file mode 100644 index 0000000000000000000000000000000000000000..50350ae374dcaf62e00d6791615d7405f9b483e3 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-199808.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d85909933fc228b02f9b1b7efa3b748b424cd874236be8e34e67ed58cf5f49ea +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-199808.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-199808.pt new file mode 100644 index 0000000000000000000000000000000000000000..de26e511fedee39c2cc71ecc8b80963df53df7ef --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-199808.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e606b378b83db87ab4aff35cec2bae9aa241a76717bc08a94daa2143ec1d8a1 +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-299840.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-299840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3387ad50aa0ea440468f2164c311e75a9db19523 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-299840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a894912e1aadd69727ca4db48285cc2a1efa55c571bbfa9e055012d04dc7cab5 +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-299840.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-299840.pt new file mode 100644 index 0000000000000000000000000000000000000000..e2faefa53e5d4a1bb4ef51fd6382ddda553f79d5 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-299840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eb8184fff5d9f859031975a430141cedc050824136a152903e26947cfd36779 +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-399964.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-399964.onnx new file mode 100644 index 0000000000000000000000000000000000000000..97a7d19a2d22be02f4e696a175b82134d590e451 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-399964.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9147dc473093a49fc1a2e2b253de9032000cade2fdcd494e99c93697de2754f5 +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-399964.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-399964.pt new file mode 100644 index 0000000000000000000000000000000000000000..cc40c8091012186d6d00bda06247ded9c59dcab8 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-399964.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60518ed6cbc63e382efe25bef2c81b0d0edc47c08bd13182fbc398bb3732e0f +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-499840.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-499840.onnx new file mode 100644 index 0000000000000000000000000000000000000000..030f47fdd730a2bc5e4bf487c0301e1dc26ba369 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-499840.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a22736ba4b37a1233389c7435f035e26d56d58dc5cafeaa42a45cd62924043 +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-499840.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-499840.pt new file mode 100644 index 0000000000000000000000000000000000000000..b84ed03cb3150605d073efc421ecebeb1b8af210 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-499840.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97478dac6348e2f332c108da03ed8703ca8d6934ea207db7fa479ee98979a2e +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-599872.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-599872.onnx new file mode 100644 index 0000000000000000000000000000000000000000..3564a597c6231f7b33bd2de4776163b1229e66f9 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-599872.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c370a07c82de64a2b4f279f7f87c2cb37966de16d31d8f6ef22848ffb14175fb +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-599872.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-599872.pt new file mode 100644 index 0000000000000000000000000000000000000000..bdaaf610870b0d5a46c3e0875e0b8352be65d0d4 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-599872.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eede99d3249086eb03b0a66b9fabd8a242e37ac4dd0e12c6657d5af037be636 +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-699904.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-699904.onnx new file mode 100644 index 0000000000000000000000000000000000000000..60330800477f59046041a18498e960dd7283c669 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-699904.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d136e9ab8e13617b3c1ea01b467488e79ecfb04f549b45caaefa89503c48886 +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-699904.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-699904.pt new file mode 100644 index 0000000000000000000000000000000000000000..089940dc7719415b1722b1c425945264fb0576b6 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-699904.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:363087acfc6e12f8480b8791c900c202a599fc423bbd2bd6c75e5d358dc4f805 +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-799936.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-799936.onnx new file mode 100644 index 0000000000000000000000000000000000000000..493eece713c98d19a327d68f1400cad45140e765 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-799936.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c576be8c9b1ab94db2a18aa3e06a82c4a316155d050ab447ab2f64dfa9381eb8 +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-799936.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-799936.pt new file mode 100644 index 0000000000000000000000000000000000000000..b57e965dc3de2e9a87dc2f9049d74d5158347fab --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-799936.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dea18e90144dc87b6ecbe52ebae19c288e314ad8814bf8071b006a0c5fcc971b +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-899904.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-899904.onnx new file mode 100644 index 0000000000000000000000000000000000000000..7fb941f524e11a60237cf225dadb096f4cafb9a3 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-899904.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c53bd078cdb2a6f4a854750c4a746f8548241977c8aa3e1f701440b9b1ec9ac1 +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-899904.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-899904.pt new file mode 100644 index 0000000000000000000000000000000000000000..560d7ac8552d1e35c505cf43377ca4acfedf7de5 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-899904.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b73209adfa0f6399ec929f4958007458814144b08fddffc48bc597fc00822d92 +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-999936.onnx b/results/tau_agent_A8_1M/TauAgent/TauAgent-999936.onnx new file mode 100644 index 0000000000000000000000000000000000000000..fbea24becb674d2651b769bd294b72411fff5721 --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-999936.onnx @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9401ddc1321ddb0c274e9e08f580abea972aa1dfb02183994191bec5ae2f41b3 +size 2186395 diff --git a/results/tau_agent_A8_1M/TauAgent/TauAgent-999936.pt b/results/tau_agent_A8_1M/TauAgent/TauAgent-999936.pt new file mode 100644 index 0000000000000000000000000000000000000000..e84ec6e16b76a6ee3c179434d18a19604ecf1bef --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/TauAgent-999936.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f55f8b339de9f8042601b9ee76454268d65451fbaf045dc53f8a15cb2c45346f +size 15534102 diff --git a/results/tau_agent_A8_1M/TauAgent/checkpoint.pt b/results/tau_agent_A8_1M/TauAgent/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..a55b081a97b4864fee4e624dae9ebfeef7f0b7ee --- /dev/null +++ b/results/tau_agent_A8_1M/TauAgent/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d58fd65e2610ba2ea21ba0cd72e02d4c302c4cc74f31619bd2482a367f3164c +size 15533332 diff --git a/results/tau_agent_A8_1M/configuration.yaml b/results/tau_agent_A8_1M/configuration.yaml new file mode 100644 index 0000000000000000000000000000000000000000..3852d5d48f72c160940d0babab967645fc465574 --- /dev/null +++ b/results/tau_agent_A8_1M/configuration.yaml @@ -0,0 +1,93 @@ +default_settings: null +behaviors: + TauAgent: + trainer_type: ppo + hyperparameters: + batch_size: 256 + buffer_size: 4096 + learning_rate: 3.0e-05 + beta: 0.005 + epsilon: 0.2 + lambd: 0.95 + num_epoch: 6 + shared_critic: false + learning_rate_schedule: linear + beta_schedule: linear + epsilon_schedule: linear + checkpoint_interval: 100000 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: + sequence_length: 256 + memory_size: 256 + goal_conditioning_type: hyper + deterministic: false + reward_signals: + extrinsic: + gamma: 0.99 + strength: 1.0 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + curiosity: + gamma: 0.995 + strength: 0.1 + network_settings: + normalize: true + hidden_units: 256 + num_layers: 4 + vis_encode_type: simple + memory: null + goal_conditioning_type: hyper + deterministic: false + learning_rate: 0.0003 + encoding_size: null + init_path: null + keep_checkpoints: 10 + even_checkpoints: false + max_steps: 1000000 + time_horizon: 256 + summary_freq: 10000 + threaded: true + self_play: null + behavioral_cloning: null +env_settings: + env_path: .\Build + env_args: null + base_port: 5005 + num_envs: 1 + num_areas: 1 + timeout_wait: 300 + seed: -1 + max_lifetime_restarts: 10 + restarts_rate_limit_n: 1 + restarts_rate_limit_period_s: 60 +engine_settings: + width: 84 + height: 84 + quality_level: 5 + time_scale: 20 + target_frame_rate: -1 + capture_frame_rate: 60 + no_graphics: false +environment_parameters: null +checkpoint_settings: + run_id: tau_agent_sac_A8 + initialize_from: null + load_model: false + resume: false + force: true + train_model: false + inference: false + results_dir: results +torch_settings: + device: cuda +debug: false