experiment 2 with rl zoo

.gitattributes

@@ -30,3 +30,4 @@ 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

@@ -8,29 +8,68 @@ tags:
 model-index:
 - name: PPO
   results:
-  - metrics:
-    - type: mean_reward
-      value: 175.65 +/- 69.08
-      name: mean_reward
-    task:
+  - task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: LunarLander-v2
       type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: 267.87 +/- 21.10
+      name: mean_reward
+      verified: false
 ---
 
 # **PPO** Agent playing **LunarLander-v2**
 This is a trained model of a **PPO** agent playing **LunarLander-v2**
-using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
+and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
 
-## Usage (with Stable-baselines3)
-TODO: Add your code
+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)
 
-```python
-from stable_baselines3 import ...
-from huggingface_sb3 import load_from_hub
+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 ppo --env LunarLander-v2 -orga CoreyMorris -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env LunarLander-v2  -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 ppo --env LunarLander-v2 -orga CoreyMorris -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env LunarLander-v2  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env LunarLander-v2 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env LunarLander-v2 -f logs/ -orga CoreyMorris
+```
+
+## Hyperparameters
+```python
+OrderedDict([('batch_size', 64),
+             ('ent_coef', 0.01),
+             ('gae_lambda', 0.98),
+             ('gamma', 0.999),
+             ('n_envs', 16),
+             ('n_epochs', 4),
+             ('n_steps', 1024),
+             ('n_timesteps', 1000000.0),
+             ('policy', 'MlpPolicy'),
+             ('normalize', False)])
 ```

args.yml

@@ -0,0 +1,83 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - conf_file
+    - null
+  - - device
+    - auto
+  - - env
+    - LunarLander-v2
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 10
+  - - eval_freq
+    - 10000
+  - - gym_packages
+    - []
+  - - hyperparams
+    - null
+  - - log_folder
+    - logs
+  - - log_interval
+    - -1
+  - - 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
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - 10000
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 2587859772
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/LunarLander-v2__ppo__2587859772__1674536198
+  - - track
+    - true
+  - - trained_agent
+    - logs/ppo/LunarLander-v2_1/rl_model_990000_steps.zip
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - null
+  - - wandb_project_name
+    - lander
+  - - wandb_tags
+    - []
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,19 @@
+!!python/object/apply:collections.OrderedDict
+- - - batch_size
+    - 64
+  - - ent_coef
+    - 0.01
+  - - gae_lambda
+    - 0.98
+  - - gamma
+    - 0.999
+  - - n_envs
+    - 16
+  - - n_epochs
+    - 4
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 1000000.0
+  - - policy
+    - MlpPolicy

env_kwargs.yml

@@ -0,0 +1 @@
+{}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6833ae16701effac68aa0e4356ce19f36a5e7c89d4584c5e30ea9746bd1a816e
-size 147128
+oid sha256:71c23f28c774b4c1ea048a23e6f96de139eabab057c2fd6f95cb6803823942bd
+size 150362

ppo-LunarLander-v2/_stable_baselines3_version

@@ -1 +1 @@
-1.6.0
+1.7.0

ppo-LunarLander-v2/data

@@ -3,20 +3,21 @@
         ":type:": "<class 'abc.ABCMeta'>",
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
-        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param sde_net_arch: Network architecture for extracting features\n        when using gSDE. If None, the latent features from the policy will be used.\n        Pass an empty list to use the states as features.\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\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 ActorCriticPolicy.__init__ at 0x7efca12a3d40>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7efca12a3dd0>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7efca12a3e60>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7efca12a3ef0>",
-        "_build": "<function ActorCriticPolicy._build at 0x7efca12a3f80>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7efca12aa050>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7efca12aa0e0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7efca12aa170>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7efca12aa200>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7efca12aa290>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7efca12aa320>",
+        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ActorCriticPolicy.__init__ at 0x7fbd0bd80940>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbd0bd809d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbd0bd80a60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbd0bd80af0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fbd0bd80b80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fbd0bd80c10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fbd0bd80ca0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbd0bd80d30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fbd0bd80dc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbd0bd80e50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbd0bd80ee0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbd0bd80f70>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7efca12f95a0>"
+        "_abc_impl": "<_abc_data object at 0x7fbd0bd7c6c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
@@ -35,29 +36,26 @@
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWVggAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUaAeTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        ":serialized:": "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",
         "n": 4,
         "_shape": [],
         "dtype": "int64",
-        "_np_random": null
+        "_np_random": "RandomState(MT19937)"
     },
-    "n_envs": 16,
-    "num_timesteps": 507904,
-    "_total_timesteps": 500000,
+    "n_envs": 1,
+    "num_timesteps": 1015808,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
-    "seed": null,
+    "seed": 0,
     "action_noise": null,
-    "start_time": 1662401121.3373034,
+    "start_time": 1674536206442318020,
     "learning_rate": 0.0003,
-    "tensorboard_log": null,
+    "tensorboard_log": "runs/LunarLander-v2__ppo__2587859772__1674536198/LunarLander-v2",
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
-    },
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
+    "_last_obs": null,
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
         ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
@@ -69,13 +67,13 @@
     "_current_progress_remaining": -0.015808000000000044,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 124,
+    "_n_updates": 488,
     "n_steps": 1024,
     "gamma": 0.999,
     "gae_lambda": 0.98,
@@ -86,7 +84,7 @@
     "n_epochs": 4,
     "clip_range": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "clip_range_vf": null,
     "normalize_advantage": true,

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615482bf1d18fb9def712ca5417a93e97c47353b6f34f56290b50310c85c4e3b
-size 87865
+oid sha256:206c1a8e05b2d4c3b27f04b11e76a4ce6cf68c3bca6cbcf57f717ba7a40b41eb
+size 88057

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5af2d7d72516c7e8e9cfee5da5a430645386b082392803c281c94163dc7435
-size 43201
+oid sha256:a640bcc82ec6b418276179fb19af01d9c3e41d7ec1c4fe2a8d350826541be9fc
+size 43393

ppo-LunarLander-v2/system_info.txt

@@ -1,7 +1,7 @@
-OS: Linux-5.4.188+-x86_64-with-Ubuntu-18.04-bionic #1 SMP Sun Apr 24 10:03:06 PDT 2022
-Python: 3.7.13
-Stable-Baselines3: 1.6.0
-PyTorch: 1.12.1+cu113
-GPU Enabled: True
-Numpy: 1.21.6
-Gym: 0.21.0
+- OS: Linux-5.4.0-137-generic-x86_64-with-glibc2.17 # 154-Ubuntu SMP Thu Jan 5 17:03:22 UTC 2023
+- Python: 3.8.15
+- Stable-Baselines3: 1.7.0
+- PyTorch: 1.13.1
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Gym: 0.21.0

results.json

@@ -1 +1 @@
-{"mean_reward": 175.6504080777763, "std_reward": 69.08280280503445, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-09-05T18:41:50.320343"}
+{"mean_reward": 267.8749631, "std_reward": 21.100035115092965, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-24T01:06:43.544303"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e83039644a6f6388468c54e7960f1468459c6ad482d6972b3c6767859dc33a
+size 107166