First model with optuna trained hyperparameters

A2C-with-optuna-tuned.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d26b8451fdd122d1f90dcf40eeb20d518a3fc3564003fcb2ea347196a324838
+size 96571

A2C-with-optuna-tuned/_stable_baselines3_version

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

A2C-with-optuna-tuned/data

@@ -0,0 +1,111 @@
+{
+    "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 0x7df0e14aecb0>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7df0e14aed40>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7df0e14aedd0>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7df0e14aee60>",
+        "_build": "<function ActorCriticPolicy._build at 0x7df0e14aeef0>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7df0e14aef80>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7df0e14af010>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7df0e14af0a0>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7df0e14af130>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7df0e14af1c0>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7df0e14af250>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7df0e14af2e0>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7df0e1443140>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWV4QAAAAAAAAB9lCiMCG5ldF9hcmNolH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldYwNYWN0aXZhdGlvbl9mbpSMG3RvcmNoLm5uLm1vZHVsZXMuYWN0aXZhdGlvbpSMBFJlTFWUk5SMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
+        "net_arch": {
+            "pi": [
+                64,
+                64
+            ],
+            "vf": [
+                64,
+                64
+            ]
+        },
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
+        "optimizer_kwargs": {
+            "alpha": 0.99,
+            "eps": 1e-05,
+            "weight_decay": 0
+        }
+    },
+    "num_timesteps": 1000320,
+    "_total_timesteps": 1000000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1698967319550806542,
+    "learning_rate": 0.0024773196622019287,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAKkDvb6uL7C+jtkjO2lvwz6UJa6+0oYKvu4GXj2keyK+jeLBvgnffbxgVQm8LnhVvTm1pr7Syko9akjUvML+oTxF4729fIESv37Y9rwo7VM+Af+4vs/7Jb7oLM+8gvNtPiBL1b5Tx1W+V7C+PNAv5D5yUZe+CB4/ProbjLwBskC+0puyvrhZYr42s3S7MxwyPtv71r2BnmW+XVUou3PcR72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwpLBIaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYKAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwqFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": null,
+    "_episode_num": 0,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.000320000000000098,
+    "_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": 1563,
+    "observation_space": {
+        ":type:": "<class 'gymnasium.spaces.box.Box'>",
+        ":serialized:": "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",
+        "dtype": "float32",
+        "bounded_below": "[ True  True  True  True]",
+        "bounded_above": "[ True  True  True  True]",
+        "_shape": [
+            4
+        ],
+        "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]",
+        "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]",
+        "_np_random": null
+    },
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "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",
+        "n": "2",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 10,
+    "n_steps": 64,
+    "gamma": 0.9947122859856005,
+    "gae_lambda": 1.0,
+    "ent_coef": 0.0,
+    "vf_coef": 0.5,
+    "max_grad_norm": 4.893543457481427,
+    "normalize_advantage": false,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

A2C-with-optuna-tuned/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1373bcec0b9e4c3b3d7800a79afdf11022f51d7df690f7d58f603c6acd62c103
+size 40370

A2C-with-optuna-tuned/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842542893747a64021d7462934de280f2b50e5885da903afe6e07453779503ea
+size 41074

A2C-with-optuna-tuned/pytorch_variables.pth

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

A2C-with-optuna-tuned/system_info.txt

@@ -0,0 +1,9 @@
+- OS: Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.0.0a5
+- PyTorch: 2.1.0+cu118
+- GPU Enabled: False
+- Numpy: 1.23.5
+- Cloudpickle: 2.2.1
+- Gymnasium: 0.28.1
+- OpenAI Gym: 0.25.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: A2C
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 500.00 +/- 0.00
+      name: mean_reward
+      verified: false
+---
+
+# **A2C** Agent playing **CartPole-v1**
+This is a trained model of a **A2C** agent playing **CartPole-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 0x7df0e14aecb0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7df0e14aed40>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7df0e14aedd0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7df0e14aee60>", "_build": "<function ActorCriticPolicy._build at 0x7df0e14aeef0>", "forward": "<function ActorCriticPolicy.forward at 0x7df0e14aef80>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7df0e14af010>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7df0e14af0a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7df0e14af130>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7df0e14af1c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7df0e14af250>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7df0e14af2e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7df0e1443140>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWV4QAAAAAAAAB9lCiMCG5ldF9hcmNolH2UKIwCcGmUXZQoS0BLQGWMAnZmlF2UKEtAS0BldYwNYWN0aXZhdGlvbl9mbpSMG3RvcmNoLm5uLm1vZHVsZXMuYWN0aXZhdGlvbpSMBFJlTFWUk5SMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "net_arch": {"pi": [64, 64], "vf": [64, 64]}, "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000320, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1698967319550806542, "learning_rate": 0.0024773196622019287, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVFQEAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJagAAAAAAAAAKkDvb6uL7C+jtkjO2lvwz6UJa6+0oYKvu4GXj2keyK+jeLBvgnffbxgVQm8LnhVvTm1pr7Syko9akjUvML+oTxF4729fIESv37Y9rwo7VM+Af+4vs/7Jb7oLM+8gvNtPiBL1b5Tx1W+V7C+PNAv5D5yUZe+CB4/ProbjLwBskC+0puyvrhZYr42s3S7MxwyPtv71r2BnmW+XVUou3PcR72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwpLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVfQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYKAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwqFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.000320000000000098, "_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": 1563, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "low_repr": "[-4.8000002e+00 -3.4028235e+38 -4.1887903e-01 -3.4028235e+38]", "high_repr": "[4.8000002e+00 3.4028235e+38 4.1887903e-01 3.4028235e+38]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "2", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 10, "n_steps": 64, "gamma": 0.9947122859856005, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 4.893543457481427, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0a5", "PyTorch": "2.1.0+cu118", "GPU Enabled": "False", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "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": "2023-11-03T02:53:02.463675"}