Push to Hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst 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 +1,84 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 152.20 +/- 2.86
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **CartPole-v1**
+This is a trained model of a **DQN** agent playing **CartPole-v1**
+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
+
+Install the RL Zoo (with SB3 and SB3-Contrib):
+```bash
+pip install rl_zoo3
+```
+
+```
+# Download model and save it into the logs/ folder
+python -m rl_zoo3.load_from_hub --algo dqn --env CartPole-v1 -orga nsanghi -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env CartPole-v1  -f logs/
+```
+
+If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
+```
+python -m rl_zoo3.load_from_hub --algo dqn --env CartPole-v1 -orga nsanghi -f logs/
+python -m rl_zoo3.enjoy --algo dqn --env CartPole-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo dqn --env CartPole-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo dqn --env CartPole-v1 -f logs/ -orga nsanghi
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 64),
+             ('buffer_size', 100000),
+             ('exploration_final_eps', 0.04),
+             ('exploration_fraction', 0.16),
+             ('gamma', 0.99),
+             ('gradient_steps', 128),
+             ('learning_rate', 0.0023),
+             ('learning_starts', 1000),
+             ('n_timesteps', 50000.0),
+             ('policy', 'MlpPolicy'),
+             ('policy_kwargs', 'dict(net_arch=[256, 256])'),
+             ('target_update_interval', 10),
+             ('train_freq', 256),
+             ('normalize', False)])
+```
+
+# Environment Arguments
+```python
+{'render_mode': 'rgb_array'}
+```

args.yml

@@ -0,0 +1,81 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - dqn
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - CartPole-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - 400
+  - - max_total_trials
+    - null
+  - - n_eval_envs
+    - 1
+  - - 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
+  - - progress
+    - true
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - 10000
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 4205676148
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/CartPole-v1__dqn__4205676148__1698256789
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - dqn-cartpole
+  - - wandb_tags
+    - []

config.yml

@@ -0,0 +1,27 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 64
+  - - buffer_size
+    - 100000
+  - - exploration_final_eps
+    - 0.04
+  - - exploration_fraction
+    - 0.16
+  - - gamma
+    - 0.99
+  - - gradient_steps
+    - 128
+  - - learning_rate
+    - 0.0023
+  - - learning_starts
+    - 1000
+  - - n_timesteps
+    - 50000.0
+  - - policy
+    - MlpPolicy
+  - - policy_kwargs
+    - dict(net_arch=[256, 256])
+  - - target_update_interval
+    - 10
+  - - train_freq
+    - 256

dqn-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de6a6e62ebce57ab258e1e17e873086d91349745f1365c364002c193661356cf
+size 1107479

dqn-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

dqn-CartPole-v1/data

@@ -0,0 +1,127 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.dqn.policies",
+        "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}",
+        "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
+        "__init__": "<function DQNPolicy.__init__ at 0x7f7e7d8d8310>",
+        "_build": "<function DQNPolicy._build at 0x7f7e7d8d83a0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7f7e7d8d8430>",
+        "forward": "<function DQNPolicy.forward at 0x7f7e7d8d84c0>",
+        "_predict": "<function DQNPolicy._predict at 0x7f7e7d8d8550>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f7e7d8d85e0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f7e7d8d8670>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f7e7d8cadc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        "net_arch": [
+            256,
+            256
+        ]
+    },
+    "num_timesteps": 30000,
+    "_total_timesteps": 50000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1698256792389686494,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/CartPole-v1__dqn__4205676148__1698256789/CartPole-v1",
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAMTQED0Ugzw/oNLJPdyrmL6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 379,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.40002000000000004,
+    "_stats_window_size": 100,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 14592,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_shape": [
+            4
+        ],
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "2",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
+    "buffer_size": 1,
+    "batch_size": 64,
+    "learning_starts": 1000,
+    "tau": 1.0,
+    "gamma": 0.99,
+    "gradient_steps": 128,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f7e7d8bcaf0>",
+        "add": "<function ReplayBuffer.add at 0x7f7e7d8bcb80>",
+        "sample": "<function ReplayBuffer.sample at 0x7f7e7d8bcc10>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f7e7d8bcca0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7f7e7d8bcd30>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f7e7d838440>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYgAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RNAAFoAIwSVHJhaW5GcmVxdWVuY3lVbml0lJOUjARzdGVwlIWUUpSGlIGULg=="
+    },
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.04,
+    "exploration_fraction": 0.16,
+    "target_update_interval": 10,
+    "_n_calls": 29999,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.04,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

dqn-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d4396f0ff5bb988d5441e07812ed5e22748221d77e0758e3dcf4cf9ea38276
+size 545519

dqn-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc0592d099dd214d518d11bf823825f887a715cdcb2ac4e2d2320749a0660961
+size 544641

dqn-CartPole-v1/pytorch_variables.pth

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

dqn-CartPole-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.90.1-microsoft-standard-WSL2-x86_64-with-glibc2.35 # 1 SMP Fri Jan 27 02:56:13 UTC 2023
+- Python: 3.10.6
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.0.1+cu117
+- GPU Enabled: False
+- Numpy: 1.25.1
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.26.2

env_kwargs.yml

@@ -0,0 +1 @@
+render_mode: rgb_array

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321923938fd02e6ac892e5b5764290a7da3aadb46767d53c937ec60f513a3559
+size 90679

results.json

@@ -0,0 +1 @@
+{"mean_reward": 152.2, "std_reward": 2.85657137141714, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-25T23:47:14.927431"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f5619a5177ffcc0f9b123aeced9c27be9e0719a9f3de4d163424bb8780cb6a
+size 11172