Push to Hub

DQN-CartPole-v1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce9d509edf1d87b70794e2b72a29c27e0a1524a5d62987d1ca715f7382a1882
+size 1108125

DQN-CartPole-v1/_stable_baselines3_version

@@ -0,0 +1 @@
+2.1.0

DQN-CartPole-v1/data

@@ -0,0 +1,130 @@
+{
+    "policy_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=",
+        "__module__": "stable_baselines3.dqn.policies",
+        "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}",
+        "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\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 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 DQNPolicy.__init__ at 0x2a0c7a700>",
+        "_build": "<function DQNPolicy._build at 0x2a0c7a790>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x2a0c7a820>",
+        "forward": "<function DQNPolicy.forward at 0x2a0c7a8b0>",
+        "_predict": "<function DQNPolicy._predict at 0x2a0c7a940>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x2a0c7a9d0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x2a0c7aa60>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x2a0c7df00>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {
+        ":type:": "<class 'dict'>",
+        ":serialized:": "gAWVUQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChNAAFNAAFldS4=",
+        "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>",
+        "net_arch": [
+            256,
+            256
+        ]
+    },
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000.0,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1712635922969288000,
+    "learning_rate": 0.0001,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAOEzGj+IzA4/r5l2PTgeWz6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAOhXFj+n9kA/dJl+PU/6x72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 4160,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": 0.0,
+    "_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": 12500,
+    "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": 1,
+    "buffer_size": 1000000,
+    "batch_size": 32,
+    "learning_starts": 50000,
+    "tau": 1.0,
+    "gamma": 0.99,
+    "gradient_steps": 1,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ",
+        "__init__": "<function ReplayBuffer.__init__ at 0x2a0c50f70>",
+        "add": "<function ReplayBuffer.add at 0x2a0c60040>",
+        "sample": "<function ReplayBuffer.sample at 0x2a0c600d0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x2a0c60160>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x2a0c5e280>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x2a0c5f300>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
+    },
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.05,
+    "exploration_fraction": 0.1,
+    "target_update_interval": 10000,
+    "_n_calls": 100000,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.05,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

DQN-CartPole-v1/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efccc72b2b3a7b63f657694038e3aa8fbc6ef00d6772050e0951fa16cd72ced3
+size 545952

DQN-CartPole-v1/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01125850767ff38a96281721cc356f6012ae6e7495e6dd58ab781a43313dc70d
+size 545074

DQN-CartPole-v1/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebdad4b9cfe9cd22a3abadb5623bf7bb1f6eb2e408740245eb3f2044b0adc018
+size 864

DQN-CartPole-v1/system_info.txt

@@ -0,0 +1,9 @@
+- OS: macOS-14.2.1-arm64-arm-64bit Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:34 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T8103
+- Python: 3.9.19
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.2.1
+- GPU Enabled: False
+- Numpy: 1.26.4
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.26.2

README.md

@@ -0,0 +1,37 @@
+---
+library_name: stable-baselines3
+tags:
+- CartPole-v1
+- deep-reinforcement-learning
+- reinforcement-learning
+- stable-baselines3
+model-index:
+- name: DQN
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: CartPole-v1
+      type: CartPole-v1
+    metrics:
+    - type: mean_reward
+      value: 213.40 +/- 20.11
+      name: mean_reward
+      verified: false
+---
+
+# **DQN** Agent playing **CartPole-v1**
+This is a trained model of a **DQN** 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:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmRxbi5wb2xpY2llc5SMCURRTlBvbGljeZSTlC4=", "__module__": "stable_baselines3.dqn.policies", "__annotations__": "{'q_net': <class 'stable_baselines3.dqn.policies.QNetwork'>, 'q_net_target': <class 'stable_baselines3.dqn.policies.QNetwork'>}", "__doc__": "\n    Policy class with Q-Value Net and target net for DQN\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 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 DQNPolicy.__init__ at 0x2a0c7a700>", "_build": "<function DQNPolicy._build at 0x2a0c7a790>", "make_q_net": "<function DQNPolicy.make_q_net at 0x2a0c7a820>", "forward": "<function DQNPolicy.forward at 0x2a0c7a8b0>", "_predict": "<function DQNPolicy._predict at 0x2a0c7a940>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x2a0c7a9d0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x2a0c7aa60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x2a0c7df00>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVUQAAAAAAAAB9lCiMDWFjdGl2YXRpb25fZm6UjBt0b3JjaC5ubi5tb2R1bGVzLmFjdGl2YXRpb26UjARSZUxVlJOUjAhuZXRfYXJjaJRdlChNAAFNAAFldS4=", "activation_fn": "<class 'torch.nn.modules.activation.ReLU'>", "net_arch": [256, 256]}, "num_timesteps": 100000, "_total_timesteps": 100000.0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1712635922969288000, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAOEzGj+IzA4/r5l2PTgeWz6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAOhXFj+n9kA/dJl+PU/6x72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_episode_num": 4160, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_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": 12500, "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": 1, "buffer_size": 1000000, "batch_size": 32, "learning_starts": 50000, "tau": 1.0, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__doc__": "\n    Replay buffer used in off-policy algorithms like SAC/TD3.\n\n    :param buffer_size: Max number of element in the buffer\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param device: PyTorch device\n    :param n_envs: Number of parallel environments\n    :param optimize_memory_usage: Enable a memory efficient variant\n        of the replay buffer which reduces by almost a factor two the memory used,\n        at a cost of more complexity.\n        See https://github.com/DLR-RM/stable-baselines3/issues/37#issuecomment-637501195\n        and https://github.com/DLR-RM/stable-baselines3/pull/28#issuecomment-637559274\n        Cannot be used in combination with handle_timeout_termination.\n    :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n        separately and treat the task as infinite horizon task.\n        https://github.com/DLR-RM/stable-baselines3/issues/284\n    ", "__init__": "<function ReplayBuffer.__init__ at 0x2a0c50f70>", "add": "<function ReplayBuffer.add at 0x2a0c60040>", "sample": "<function ReplayBuffer.sample at 0x2a0c600d0>", "_get_samples": "<function ReplayBuffer._get_samples at 0x2a0c60160>", "_maybe_cast_dtype": "<staticmethod object at 0x2a0c5e280>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x2a0c5f300>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "exploration_initial_eps": 1.0, "exploration_final_eps": 0.05, "exploration_fraction": 0.1, "target_update_interval": 10000, "_n_calls": 100000, "max_grad_norm": 10, "exploration_rate": 0.05, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "exploration_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "macOS-14.2.1-arm64-arm-64bit Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:34 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T8103", "Python": "3.9.19", "Stable-Baselines3": "2.1.0", "PyTorch": "2.2.1", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 213.4, "std_reward": 20.110693672770218, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-09T09:51:32.824633"}