Acrobot-v1 - erster (schlechter) Versuch

Acrobot-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcd318837a34947f8cb8547bb632e70225b4646f90ebb50afd8792ea3bb6b064
+size 142296

Acrobot-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.0.0a5

Acrobot-v1/data

@@ -0,0 +1,99 @@
+{
+    "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 0x78af0c95d630>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78af0c95d6c0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78af0c95d750>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78af0c95d7e0>",
+        "_build": "<function ActorCriticPolicy._build at 0x78af0c95d870>",
+        "forward": "<function ActorCriticPolicy.forward at 0x78af0c95d900>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x78af0c95d990>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78af0c95da20>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x78af0c95dab0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78af0c95db40>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78af0c95dbd0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x78af0c95dc60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x78af0c90acc0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 32768,
+    "_total_timesteps": 10000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1731776505599120364,
+    "learning_rate": 0.0003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -2.2768,
+    "_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": 10,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True]",
+        "_shape": [
+            6
+        ],
+        "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]",
+        "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "3",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
+    },
+    "n_envs": 16,
+    "n_steps": 2048,
+    "gamma": 0.99,
+    "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:": "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"
+    },
+    "clip_range_vf": null,
+    "normalize_advantage": true,
+    "target_kl": null,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

Acrobot-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da565c02c4702d6886281bd3639ac151dcc47acce04ab3b0fe0b09febb3e9aa6
+size 85802

Acrobot-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2e44d2515017a519d0fad9374a402b949d0fe3fdb3b96f5b99fddfdeb07dc8
+size 42482

Acrobot-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
+size 864

Acrobot-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.5.1+cu121
+- GPU Enabled: True
+- Numpy: 1.26.4
+- Cloudpickle: 3.1.0
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- Acrobot-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: Acrobot-v1
+      type: Acrobot-v1
+    metrics:
+    - type: mean_reward
+      value: -500.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **PPO** Agent playing **Acrobot-v1**
+This is a trained model of a **PPO** agent playing **Acrobot-v1**
+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 0x78af0c95d630>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x78af0c95d6c0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x78af0c95d750>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x78af0c95d7e0>", "_build": "<function ActorCriticPolicy._build at 0x78af0c95d870>", "forward": "<function ActorCriticPolicy.forward at 0x78af0c95d900>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x78af0c95d990>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x78af0c95da20>", "_predict": "<function ActorCriticPolicy._predict at 0x78af0c95dab0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x78af0c95db40>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x78af0c95dbd0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x78af0c95dc60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x78af0c90acc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 32768, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1731776505599120364, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -2.2768, "_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": 10, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True]", "_shape": [6], "low": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high": "[ 1.        1.        1.        1.       12.566371 28.274334]", "low_repr": "[ -1.        -1.        -1.        -1.       -12.566371 -28.274334]", "high_repr": "[ 1.        1.        1.        1.       12.566371 28.274334]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "n_envs": 16, "n_steps": 2048, "gamma": 0.99, "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:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.5.1+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": -500.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-11-16T17:03:20.368358"}