Upload model to Hugging Face

PPO-punish-stag-at-end.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db8294853a1a21635424a7240a9226a4a819c6535824d20ea1cbaa7f785b076d
+size 150410

PPO-punish-stag-at-end/_stable_baselines3_version

@@ -0,0 +1 @@
+1.7.0

PPO-punish-stag-at-end/data

@@ -0,0 +1,95 @@
+{
+    "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 0x7f036d7f51b0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f036d7f5240>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f036d7f52d0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f036d7f5360>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f036d7f53f0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f036d7f5480>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f036d7f5510>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f036d7f55a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f036d7f5630>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f036d7f56c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f036d7f5750>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f036d7f57e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7f036d7e1f40>"
+    },
+    "verbose": true,
+    "policy_kwargs": {},
+    "observation_space": {
+        ":type:": "<class 'gym.spaces.box.Box'>",
+        ":serialized:": "gAWVuQEAAAAAAACMDmd5bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMBl9zaGFwZZRLCoWUjANsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWKAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAlGgLSwqFlIwBQ5R0lFKUjARoaWdolGgTKJYoAAAAAAAAAADo/UjbD0lAAADIQgAAyEIAAMhCAADIQgAAyEIAAMhCAADIQgAAyEKUaAtLCoWUaBZ0lFKUjA1ib3VuZGVkX2JlbG93lGgTKJYKAAAAAAAAAAEBAQEBAQEBAQGUaAiMAmIxlImIh5RSlChLA4wBfJROTk5K/////0r/////SwB0lGJLCoWUaBZ0lFKUjA1ib3VuZGVkX2Fib3ZllGgTKJYKAAAAAAAAAAEBAQEBAQEBAQGUaCJLCoWUaBZ0lFKUjApfbnBfcmFuZG9tlE51Yi4=",
+        "dtype": "float32",
+        "_shape": [
+            10
+        ],
+        "low": "[0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]",
+        "high": "[5.2000000e+05 3.1415927e+00 1.0000000e+02 1.0000000e+02 1.0000000e+02\n 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02]",
+        "bounded_below": "[ True  True  True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True  True  True]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gym.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu",
+        "n": 4,
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 4,
+    "num_timesteps": 204800,
+    "_total_timesteps": 200000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1681929274796697714,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAJ+ejEK6NibAAADIQgAAyEJn3o9COVryQb5kxkEhZwVCAyGlQgAAyEJDt31CTe8UwAAAyEIAAMhCtQMFQnS2lUEAAMhCyzDWQXx2pEIAAMhC3Q2GQhb3GsAAAMhCAADIQnMzNkKe2s5Ba07YQQAAyEIhIL5CAADIQv00jkL6SSTAAADIQgAAyEK6V4FCdW/8QetWxEGgHf5B8ZagQgAAyEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 1120,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "gae_lambda": 0.5,
+    "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:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null
+}

PPO-punish-stag-at-end/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da204884ac95a4da6b8b9fae1703589a0a227c0f93856b3e72e0ae87e39a240c
+size 90105

PPO-punish-stag-at-end/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff4e6623579279eabe4570e93ce6186211cc1c9f2ddd2e75179a4ec383b2086
+size 44417

PPO-punish-stag-at-end/pytorch_variables.pth

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

PPO-punish-stag-at-end/system_info.txt

@@ -0,0 +1,7 @@
+- OS: Linux-5.19.0-35-generic-x86_64-with-glibc2.35 # 36~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 17 15:17:25 UTC 2
+- Python: 3.10.9
+- Stable-Baselines3: 1.7.0
+- PyTorch: 2.0.0
+- GPU Enabled: True
+- Numpy: 1.23.5
+- Gym: 0.21.0

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- RoombaAToB-punish-stag-at-end
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: RoombaAToB-punish-stag-at-end
+      type: RoombaAToB-punish-stag-at-end
+    metrics:
+    - type: mean_reward
+      value: 19.09 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **RoombaAToB-punish-stag-at-end**
+This is a trained model of a **PPO** agent playing **RoombaAToB-punish-stag-at-end**
+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:": "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 0x7f036d7f51b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f036d7f5240>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f036d7f52d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f036d7f5360>", "_build": "<function ActorCriticPolicy._build at 0x7f036d7f53f0>", "forward": "<function ActorCriticPolicy.forward at 0x7f036d7f5480>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f036d7f5510>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f036d7f55a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7f036d7f5630>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f036d7f56c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f036d7f5750>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f036d7f57e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f036d7e1f40>"}, "verbose": true, "policy_kwargs": {}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [10], "low": "[0. 0. 0. 0. 0. 0. 0. 0. 0. 0.]", "high": "[5.2000000e+05 3.1415927e+00 1.0000000e+02 1.0000000e+02 1.0000000e+02\n 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02 1.0000000e+02]", "bounded_below": "[ True  True  True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True  True  True]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.discrete.Discrete'>", ":serialized:": "gAWViAAAAAAAAACME2d5bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpRLBIwGX3NoYXBllCmMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZROdWIu", "n": 4, "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 4, "num_timesteps": 204800, "_total_timesteps": 200000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1681929274796697714, "learning_rate": 0.0003, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAJ+ejEK6NibAAADIQgAAyEJn3o9COVryQb5kxkEhZwVCAyGlQgAAyEJDt31CTe8UwAAAyEIAAMhCtQMFQnS2lUEAAMhCyzDWQXx2pEIAAMhC3Q2GQhb3GsAAAMhCAADIQnMzNkKe2s5Ba07YQQAAyEIhIL5CAADIQv00jkL6SSTAAADIQgAAyEK6V4FCdW/8QetWxEGgHf5B8ZagQgAAyEKUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwRLCoaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1120, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.5, "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:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "system_info": {"OS": "Linux-5.19.0-35-generic-x86_64-with-glibc2.35 # 36~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Fri Feb 17 15:17:25 UTC 2", "Python": "3.10.9", "Stable-Baselines3": "1.7.0", "PyTorch": "2.0.0", "GPU Enabled": "True", "Numpy": "1.23.5", "Gym": "0.21.0"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 19.094822176426295, "std_reward": 3.552713678800501e-15, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-04-19T11:48:47.827739"}