Test

.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 +1,36 @@
+---
+library_name: stable-baselines3
+tags:
+- Pixelcopter-PLE-v0
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - metrics:
+    - type: mean_reward
+      value: -2.90 +/- 0.30
+      name: mean_reward
+    task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Pixelcopter-PLE-v0
+      type: Pixelcopter-PLE-v0
+---
+
+# **PPO** Agent playing **Pixelcopter-PLE-v0**
+This is a trained model of a **PPO** agent playing **Pixelcopter-PLE-v0**
+using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

config.json

@@ -0,0 +1 @@
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__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 0x7fbfe3cbfd40>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbfe3cbfdd0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbfe3cbfe60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbfe3cbfef0>", "_build": "<function ActorCriticPolicy._build at 0x7fbfe3cbff80>", "forward": "<function ActorCriticPolicy.forward at 0x7fbfe3cc6050>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbfe3cc60e0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fbfe3cc6170>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbfe3cc6200>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbfe3cc6290>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbfe3cc6320>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7fbfe3d1a390>"}, "verbose": 1, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "shape": [7], "low": "[-inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False]", "bounded_above": "[False False False False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gASVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=", "n": 2, "shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 1, "num_timesteps": 5120, "_total_timesteps": 5000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1656534973.8442714, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASVpgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLB4aUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMck32uQdbSbL9N9plAbYKZQTMzN0IAAARCAAAoQpR0lGIu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 20, "n_steps": 1024, "gamma": 0.999, "gae_lambda": 0.98, "ent_coef": 0.01, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 4, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"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": "1.5.0", "PyTorch": "1.11.0+cu113", "GPU Enabled": "True", "Numpy": "1.21.6", "Gym": "0.17.3"}}

ppo-PixelCopter.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abacdcc6b09ed8dd0ae77cd591b5b6396d84dc49914324792142601548ba6b3b
+size 138790

ppo-PixelCopter/_stable_baselines3_version

@@ -0,0 +1 @@
+1.5.0

ppo-PixelCopter/data

@@ -0,0 +1,94 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gASVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
+        "__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 0x7fbfe3cbfd40>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fbfe3cbfdd0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fbfe3cbfe60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fbfe3cbfef0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7fbfe3cbff80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7fbfe3cc6050>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fbfe3cc60e0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7fbfe3cc6170>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fbfe3cc6200>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fbfe3cc6290>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fbfe3cc6320>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc_data object at 0x7fbfe3d1a390>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "shape": [
+            7
+        ],
+        "low": "[-inf -inf -inf -inf -inf -inf -inf]",
+        "high": "[inf inf inf inf inf inf inf]",
+        "bounded_below": "[False False False False False False False]",
+        "bounded_above": "[False False False False False False False]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gASVgQAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLAowFc2hhcGWUKYwFZHR5cGWUjAVudW1weZRoB5OUjAJpOJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRijApfbnBfcmFuZG9tlE51Yi4=",
+        "n": 2,
+        "shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 1,
+    "num_timesteps": 5120,
+    "_total_timesteps": 5000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1656534973.8442714,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASVpgAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwFLB4aUaAOMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiiUMck32uQdbSbL9N9plAbYKZQTMzN0IAAARCAAAoQpR0lGIu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gASViQAAAAAAAACMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMDF9yZWNvbnN0cnVjdJSTlIwFbnVtcHmUjAduZGFycmF5lJOUSwCFlEMBYpSHlFKUKEsBSwGFlGgDjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYolDAQCUdJRiLg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_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:": "gASVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 20,
+    "n_steps": 1024,
+    "gamma": 0.999,
+    "gae_lambda": 0.98,
+    "ent_coef": 0.01,
+    "vf_coef": 0.5,
+    "max_grad_norm": 0.5,
+    "batch_size": 64,
+    "n_epochs": 4,
+    "clip_range": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

ppo-PixelCopter/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b0577ccde04149e9949abd2881884f9dc6658c20a6bd28a57bc3a3dbc63ec14
+size 82781

ppo-PixelCopter/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:594cce5a59c156d93fe04a61f47febc53dd5517fbe9d64b02accbc20417f2c5a
+size 42177

ppo-PixelCopter/pytorch_variables.pth

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

ppo-PixelCopter/system_info.txt

@@ -0,0 +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: 1.5.0
+PyTorch: 1.11.0+cu113
+GPU Enabled: True
+Numpy: 1.21.6
+Gym: 0.17.3

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8351de794a06ebaaa9f939d1838ed39e74c8a264d9a3b9556270b5a819a6dd72
+size 75956

results.json

@@ -0,0 +1 @@
+{"mean_reward": -2.9, "std_reward": 0.3, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-29T20:37:51.205175"}