Initial Commit

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,83 @@
+---
+library_name: stable-baselines3
+tags:
+- CarRacing-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: RecurrentPPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: 880.39 +/- 31.90
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CarRacing-v0
+      type: CarRacing-v0
+---
+
+# **RecurrentPPO** Agent playing **CarRacing-v0**
+This is a trained model of a **RecurrentPPO** agent playing **CarRacing-v0**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
+
+The RL Zoo is a training framework for Stable Baselines3
+reinforcement learning agents,
+with hyperparameter optimization and pre-trained agents included.
+
+## Usage (with SB3 RL Zoo)
+
+RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
+SB3: https://github.com/DLR-RM/stable-baselines3<br/>
+SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
+
+```
+# Download model and save it into the logs/ folder
+python -m utils.load_from_hub --algo ppo_lstm --env CarRacing-v0 -orga sb3 -f logs/
+python enjoy.py --algo ppo_lstm --env CarRacing-v0  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python train.py --algo ppo_lstm --env CarRacing-v0 -f logs/
+# Upload the model and generate video (when possible)
+python -m utils.push_to_hub --algo ppo_lstm --env CarRacing-v0 -f logs/ -orga sb3
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 128),
+             ('clip_range', 0.2),
+             ('ent_coef', 0.0),
+             ('env_wrapper',
+              [{'gym.wrappers.resize_observation.ResizeObservation': {'shape': 64}},
+               {'gym.wrappers.gray_scale_observation.GrayScaleObservation': {'keep_dim': True}}]),
+             ('frame_stack', 2),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.99),
+             ('learning_rate', 'lin_1e-4'),
+             ('max_grad_norm', 0.5),
+             ('n_envs', 8),
+             ('n_epochs', 10),
+             ('n_steps', 512),
+             ('n_timesteps', 4000000.0),
+             ('normalize', "{'norm_obs': False, 'norm_reward': True}"),
+             ('policy', 'CnnLstmPolicy'),
+             ('policy_kwargs',
+              'dict(log_std_init=-2, ortho_init=False, '
+              'enable_critic_lstm=False, activation_fn=nn.GELU, '
+              'lstm_hidden_size=128, )'),
+             ('sde_sample_freq', 4),
+             ('use_sde', True),
+             ('vf_coef', 0.5),
+             ('normalize_kwargs', {'norm_obs': False, 'norm_reward': False})])
+```
+
+# Environment Arguments
+```python
+{'verbose': 0}
+```

args.yml

@@ -0,0 +1,75 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo_lstm
+  - - device
+    - auto
+  - - env
+    - CarRacing-v0
+  - - env_kwargs
+    - verbose: 0
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 50000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 5
+  - - n_evaluations
+    - null
+  - - n_jobs
+    - 1
+  - - n_startup_trials
+    - 10
+  - - n_timesteps
+    - -1
+  - - n_trials
+    - 500
+  - - no_optim_plots
+    - false
+  - - num_threads
+    - -1
+  - - optimization_log_path
+    - null
+  - - optimize_hyperparameters
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 4020884719
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/CarRacing-v0__ppo_lstm__4020884719__1654091770
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - subproc
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3

config.yml

@@ -0,0 +1,43 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 128
+  - - clip_range
+    - 0.2
+  - - ent_coef
+    - 0.0
+  - - env_wrapper
+    - - gym.wrappers.resize_observation.ResizeObservation:
+          shape: 64
+      - gym.wrappers.gray_scale_observation.GrayScaleObservation:
+          keep_dim: true
+  - - frame_stack
+    - 2
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.99
+  - - learning_rate
+    - lin_1e-4
+  - - max_grad_norm
+    - 0.5
+  - - n_envs
+    - 8
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 512
+  - - n_timesteps
+    - 4000000.0
+  - - normalize
+    - '{''norm_obs'': False, ''norm_reward'': True}'
+  - - policy
+    - CnnLstmPolicy
+  - - policy_kwargs
+    - dict(log_std_init=-2, ortho_init=False, enable_critic_lstm=False, activation_fn=nn.GELU,
+      lstm_hidden_size=128, )
+  - - sde_sample_freq
+    - 4
+  - - use_sde
+    - true
+  - - vf_coef
+    - 0.5

env_kwargs.yml

@@ -0,0 +1 @@
+verbose: 0

ppo_lstm-CarRacing-v0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d3141843cb4b813dc9deba8949b3075b4881a983669d8a2cc38b168c9f6efe2
+size 12079576

ppo_lstm-CarRacing-v0/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.1a8

ppo_lstm-CarRacing-v0/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f0362958d26257e5fa13f0762a34f9feb0cca427539339cf1a02f042468070d
+size 7962099

ppo_lstm-CarRacing-v0/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b73e146fd2a552e8ab82f0e5560802311fb242e87a81013d2cb77cf7190df97
+size 3981301

ppo_lstm-CarRacing-v0/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
+size 431

ppo_lstm-CarRacing-v0/system_info.txt

@@ -0,0 +1,7 @@
+OS: Linux-5.13.0-41-generic-x86_64-with-debian-bullseye-sid #46~20.04.1-Ubuntu SMP Wed Apr 20 13:16:21 UTC 2022
+Python: 3.7.10
+Stable-Baselines3: 1.5.1a8
+PyTorch: 1.11.0
+GPU Enabled: True
+Numpy: 1.21.2
+Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:284a6fc21ccdd07b3b2e5f44fb18ac0e5033fc9bc5ceb92ccf519f5e21fba4d3
+size 882405

results.json

@@ -0,0 +1 @@
+{"mean_reward": 880.3853001, "std_reward": 31.89815510016426, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-01T19:27:08.325774"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79ac357a05bfd0313659d9a296a755fc52db1bb2ce51b2395df501ec9eb6bcb5
+size 143392