Initial commit

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,78 @@
+---
+library_name: stable-baselines3
+tags:
+- Pendulum-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pendulum-v1
+      type: Pendulum-v1
+    metrics:
+    - type: mean_reward
+      value: -212.04 +/- 128.60
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **Pendulum-v1**
+This is a trained model of a **PPO** agent playing **Pendulum-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 ppo --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env Pendulum-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 ppo --env Pendulum-v1 -orga qgallouedec -f logs/
+python -m rl_zoo3.enjoy --algo ppo --env Pendulum-v1  -f logs/
+```
+
+## Training (with the RL Zoo)
+```
+python -m rl_zoo3.train --algo ppo --env Pendulum-v1 -f logs/
+# Upload the model and generate video (when possible)
+python -m rl_zoo3.push_to_hub --algo ppo --env Pendulum-v1 -f logs/ -orga qgallouedec
+```
+
+## Hyperparameters
+```python
+OrderedDict([('clip_range', 0.2),
+             ('ent_coef', 0.0),
+             ('gae_lambda', 0.95),
+             ('gamma', 0.9),
+             ('learning_rate', 0.001),
+             ('n_envs', 4),
+             ('n_epochs', 10),
+             ('n_steps', 1024),
+             ('n_timesteps', 100000.0),
+             ('policy', 'MlpPolicy'),
+             ('sde_sample_freq', 4),
+             ('use_sde', True),
+             ('normalize', False)])
+```

args.yml

@@ -0,0 +1,79 @@
+!!python/object/apply:collections.OrderedDict
+- - - algo
+    - ppo
+  - - device
+    - auto
+  - - env
+    - Pendulum-v1
+  - - env_kwargs
+    - null
+  - - eval_episodes
+    - 20
+  - - eval_freq
+    - 25000
+  - - 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
+  - - progress
+    - false
+  - - pruner
+    - median
+  - - sampler
+    - tpe
+  - - save_freq
+    - -1
+  - - save_replay_buffer
+    - false
+  - - seed
+    - 1422831320
+  - - storage
+    - null
+  - - study_name
+    - null
+  - - tensorboard_log
+    - runs/Pendulum-v1__ppo__1422831320__1670942118
+  - - track
+    - true
+  - - trained_agent
+    - ''
+  - - truncate_last_trajectory
+    - true
+  - - uuid
+    - false
+  - - vec_env
+    - dummy
+  - - verbose
+    - 1
+  - - wandb_entity
+    - openrlbenchmark
+  - - wandb_project_name
+    - sb3
+  - - yaml_file
+    - null

config.yml

@@ -0,0 +1,25 @@
+!!python/object/apply:collections.OrderedDict
+- - - clip_range
+    - 0.2
+  - - ent_coef
+    - 0.0
+  - - gae_lambda
+    - 0.95
+  - - gamma
+    - 0.9
+  - - learning_rate
+    - 0.001
+  - - n_envs
+    - 4
+  - - n_epochs
+    - 10
+  - - n_steps
+    - 1024
+  - - n_timesteps
+    - 100000.0
+  - - policy
+    - MlpPolicy
+  - - sde_sample_freq
+    - 4
+  - - use_sde
+    - true

env_kwargs.yml

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

ppo-Pendulum-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f9d36d17f78a2e993e832cb1ef91d01c2a286234080085b87232f7778c1e0c
+size 143441

ppo-Pendulum-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+1.8.0a6

ppo-Pendulum-v1/data

@@ -0,0 +1,100 @@
+{
+    "policy_class": {
+        ":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 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 0x7ff656590d30>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7ff656590dc0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7ff656590e50>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7ff656590ee0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7ff656590f70>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7ff656591040>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7ff6565910d0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7ff656591160>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7ff6565911f0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7ff656591280>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7ff656591310>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7ff6565913a0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7ff656959100>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "_shape": [
+            3
+        ],
+        "low": "[-1. -1. -8.]",
+        "high": "[1. 1. 8.]",
+        "bounded_below": "[ True  True  True]",
+        "bounded_above": "[ True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVBAwAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLAYWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAADAlGgKSwGFlIwBQ5R0lFKUjARoaWdolGgSKJYEAAAAAAAAAAAAAECUaApLAYWUaBV0lFKUjA1ib3VuZGVkX2JlbG93lGgSKJYBAAAAAAAAAAGUaAeMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLAYWUaBV0lFKUjA1ib3VuZGVkX2Fib3ZllGgSKJYBAAAAAAAAAAGUaCFLAYWUaBV0lFKUjApfbnBfcmFuZG9tlIwUbnVtcHkucmFuZG9tLl9waWNrbGWUjBJfX3JhbmRvbXN0YXRlX2N0b3KUk5SMB01UMTk5MzeUaC2MFF9fYml0X2dlbmVyYXRvcl9jdG9ylJOUhpRSlH2UKIwNYml0X2dlbmVyYXRvcpSMB01UMTk5MzeUjAVzdGF0ZZR9lCiMA2tleZRoEiiWwAkAAAAAAAAAAACAU8KznIcDtZNy7Ktb6Oay8s+2gdrVBu9hoTFNoGu1zNkT5hifdJx5L8ilG4DEeQFJng9D5F3gGJOSE1XM1EopZNIIlb400J5EcnoD8K2/CnObez7pYLEG2nUDRQtufdYWausENGaDt/P1pS9p70JjQ7Vc98J3UsxGRDctCIlu0I6ud/sYtoBPe575TzLsEti5jl6FqRnKrj12LWcrQoCexe7HH/UiAV1LzyQPzBlSZERXmHCdCvUSF7XpWt47xP9BzzqxX7aH3TPYWImqos1/ez/JlLdsD0MfMZl9G2CQq7cHHRlM3sj7jroA9c+pGt4l/iAGpRb80HbjwU71ykPTAVp531BXrc2qmIU6z9Fh4TAPx7fZ1kVF+L1Irlou+4Ckky7Ys59nB7KkciTI+N5jlb62ybZt0+ZWgIA6LKLvdx/mTQtB4k1aplT/C7L9/ybKCFn2quN/7YlIkxoH1U0xdabG6rgOrR+SHMmvUwvtKB+19Ibb07mSgVQyjNAvnyADPJf3pkxylZtn7f/OVpWEaWfl6BcLwy0grrEgUK+H+8P8XWMuBginXgwzn3sy4+ZOlr45op6TtuqX0Knz/SySGDlBIK8JqKObzB6fGt+ovJHEM8KlL4veKwkLkuuMWBaex3FBdWskry5qhslxMgnk2thh8DaXmAfbuI8j0SqHMW1kleITi9ekfXx/eSi5hX1GjA/M62Zixuay1H8zH9VjsTRcGacyJ0vh1hNReDFoNsXFbLfLqaIvbLDQjY7T289ZXsupvAxu2GVTbqWst+ckPPzwH7vLikULC+weAKwxarqm+ugAXgyz774meHOsvQYuu18nvrrunjZWDvwaKuYohEwUfSnpotE9XhX99yUTc8sGPQidTfXkzm/t8MWP8it4l4VSEgDLn8GW8t2DAh8EwFa/KOGoZEGjYqZ2IMA70E+F2LqgaZlQLFMONTIx3yuN5F2e1MT4v2wdBRK9R+lGMpxIiNldyOwwxLDBTRDMhd7APidmDwQBnvaIecKFa95btwHkRBEUT5g++/I0DDg685EX4OMO2YtTPqM3PQluS4puEhAQRVukNGSh4gYDgcBPKZl4ThNf+G+E7El9fmWJcP39Sifw6Mn+GEisM1RhHY05XZHUv5W4r8kD2jSLMY+IIL2+LtQrW7it7y28+sEicLoEfYOky9ZJF6l0fR+sXEawf+REH9LvtRJ4yzfxr7KisNpr1axv1ae5CDXS+XTzuOG/BJnHvt8arnY1XWH9SdkCOeok6MI8GBCtjTCxJ5JbpI5J0i0A66mJaRW9LMfP6Cil3/cVRQ9uN2KTtV3o7rJwY4XCnj7DJmqrUwofDDl7Ek0PoN7w0Hh8YHOy8qhPw7V8ALdjZn7eYtjCQIldQvHbM1I73RtCLQvQGFMXUCJ022pGRqTvZX5XWSizqbgX6TJmI6LDF9wcpYealB7cDwelfqdpzHRmyjRbIX9b+w4uj//aDRgP2SgiOAq/D/9/0SbgK/E0FQyclhNVAkbKwXhAxKGczpvJow0mFFUAt/5fT5KAsmQTAt8p0FsrGMDTfk4RzZgqZSm+ihVRS371Tx3twpGA1goo/AIfJh8slJC3hkR1OGCN7LAPGCwbM9rHlKSU4uuhJiff196h9q1kPMld6989MfKLVkvCl7ofCRurPUW46ceJKE951sQD1v8cK0HK1JmuBTCXAelCUCIFNLGk3tMXNVmuuFF3o3xb4V4T1IAYIfBdyEVHhIIZOE/JEY79daQw8njYEtQ6YwZ6kNCBYfrjq2OglITcRdwDmINL42ro6HnbWgLZQ8Ce/EiPVBtWHwhvGUHK1FNONzRzXgT1zKEg+WAigeuK4QVIxdITM4YvUyYvpQJuJd+xGD1no7BYIKXdV4aDlsRnWSMmS+zTyTvC0+TgBMCNpMvdChjaB/XTrMVsm0vgPmCYswn067MTYWfm5oCqqmNciqoRfFL2O2mxFT1VMcKDrxHBdBUhSG5UmAerx86KAEytbsCbn6OOj8Y02VwVynzXd0WJfLioeGMZISM1eneWfTc1mQ6CpdDxJqUmU86/KsBL3Bb0S2NAqFysFJZKxDwLej8xz+xH8IxEHzlkiiNH+2IIq0663FAwi6wg6dgcryDqQ+lNDwn898nylrcYShigDrtrFBNezKx3ZjpkPCnPUeQB4hJUrYCUJy5CyytC/x1UsByKez/aSNEWnlWnzYdJf2PoKL0YfmaR3KpXzi9ax3BHPgk1cdmgdVkqevFJ0DUdTBFQj/mhaKqcaT0rKJLgy/11AhWW4nX7+kAdgR0b1iAseI0TbMDtohBuqqUZfqMfUKsdI8v2aeUd0+IqOjPBFe7TZRC7OUYmf789SRTpw9gst4tzx7tLap8JnFt2keKhqd3vBgqpvlsxvx0DcPC+bo/qIldKiAn5D7TPjeWLzJ1gmpk1mVKOyWOv/ZzlRTfe8yEsMsRcgdPxbOuxLjlOwo1uFh9NjHoOz/xbnI62I49ZzT59GUCNtAL74UqjlRoyXZ5ELEjhTn+F5fYfEkY2TnSsgKO4Wwb/xD41S4mBL7LcUyF76ybV7Yx0L6V2QGoSfyhHFqMQJs/haLPPW18mWJb/UDl90ZN9TEzcdXvZsmCeqzCagC6YDHp3fop+5nAQSnT/Byt2j7z+6cnl/aZh6oKs5xrEMmuzpLFbXNVof9hNmX5E0DQ2M8uBqqeW95p6z8ySnOxURAO28oYWsbVyeYaNlWLZrOtIMZDRjjbecSSwMLlrBhw4mZVht4DgOQxI1+P7sPHZLMf89U+5ctf1rD0r1AXgyXjzOxKvCxWMhrz6Ah19+zal/bAIpw+0V7Pq85PRQO4UeScmMwODR8jcOfILuMmo7xXhemY/JqtOncklEaGapMeGlkiefvQkx9L5EWvLn6stI4zRP4pZXx9iOz17IKJmKOVHgCIAOiheb0bwkjNkItlfYO3LzeLLPuBDNLFg7tQu5NPWy28a4nBsE/gsyEteRvF2ECYFIOJg06dzc77IWw7o+z1Q5APxLg9uvyFniYWNuJyk7rflLCmYcg1gN657CWff8YfPr0ukKOamco94X1nFdyroxHiQlRXaP91DOqMueI1pCasyRQt0jtbWwxdEVyzP3GzUZXBWqa0xXCzwe29cxg2aiwKuuAAVfaCE/Pt1cJXq8wvliF81sMDPMbowd9+uyWuExq/e+2W3wWeV3hVofoiEySjBrJPWVJW9++UocJbC0ppNw5mtHktkZqUk6kVtUgVQ4Cj4udj/bluZzcqWjIvOCJO52M+xcQY808Ei8T/lwwS9TguuzQ3e0KR7hptgNcX1/XhCvAuUaAeMAnU0lImIh5RSlChLA2gLTk5OSv////9K/////0sAdJRiTXAChZRoFXSUUpSMA3Bvc5RNcAJ1jAloYXNfZ2F1c3OUSwCMBWdhdXNzlEcAAAAAAAAAAHVidWIu",
+        "dtype": "float32",
+        "_shape": [
+            1
+        ],
+        "low": "[-2.]",
+        "high": "[2.]",
+        "bounded_below": "[ True]",
+        "bounded_above": "[ True]",
+        "_np_random": "RandomState(MT19937)"
+    },
+    "n_envs": 1,
+    "num_timesteps": 102400,
+    "_total_timesteps": 100000,
+    "_num_timesteps_at_start": 0,
+    "seed": 0,
+    "action_noise": null,
+    "start_time": 1670942120896618704,
+    "learning_rate": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "tensorboard_log": "runs/Pendulum-v1__ppo__1422831320__1670942118/Pendulum-v1",
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWV/QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL3FnYWxsb3VlZGVjL3JsLWJhc2VsaW5lczMtem9vL2Vudi9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxlL2hvbWUvcWdhbGxvdWVkZWMvcmwtYmFzZWxpbmVzMy16b28vZW52L2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP1BiTdLxqfyFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "_last_obs": null,
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": true,
+    "sde_sample_freq": 4,
+    "_current_progress_remaining": -0.02400000000000002,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 250,
+    "n_steps": 1024,
+    "gamma": 0.9,
+    "gae_lambda": 0.95,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 10,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWV/QIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMZS9ob21lL3FnYWxsb3VlZGVjL3JsLWJhc2VsaW5lczMtem9vL2Vudi9saWIvcHl0aG9uMy45L3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLgEMCAAGUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxlL2hvbWUvcWdhbGxvdWVkZWMvcmwtYmFzZWxpbmVzMy16b28vZW52L2xpYi9weXRob24zLjkvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoH32UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP8mZmZmZmZqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-Pendulum-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b519f4190cbd55fb84edd1c0f14c5fa712faa1e52ddbc1e7c9c442fc971d9d
+size 82672

ppo-Pendulum-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0ac8c7ca3be56de5681e1cadb13a6491eaa4203f64baa322bb87b11f02f4f6
+size 40510

ppo-Pendulum-v1/pytorch_variables.pth

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

ppo-Pendulum-v1/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
+- Python: 3.9.12
+- Stable-Baselines3: 1.8.0a6
+- PyTorch: 1.13.1+cu117
+- GPU Enabled: True
+- Numpy: 1.24.1
+- Gym: 0.21.0

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f4eb289d01729885fdb52bba19643f4ecf9c04ff3da8074fd87e2363893177
+size 142214

results.json

@@ -0,0 +1 @@
+{"mean_reward": -212.0426082, "std_reward": 128.60239917731104, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T14:14:57.293374"}

train_eval_metrics.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8da80f3adc71180eed2a8e41fc0f98694060005f5412b1303402eed04628f55b
+size 16508