Upload DQN CartPole-v trained agent

DQN-CartPole-v1_2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d608bec7041f68e18466a095159e2f064d927564efe32b570d3ca449a811e5d3
+size 100091

DQN-CartPole-v1_2/_stable_baselines3_version

@@ -0,0 +1 @@
+2.3.0

DQN-CartPole-v1_2/data

@@ -0,0 +1,123 @@
+{
+    "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 0x000002BC8E39A0E0>",
+        "_build": "<function DQNPolicy._build at 0x000002BC8E39A170>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x000002BC8E39A200>",
+        "forward": "<function DQNPolicy.forward at 0x000002BC8E39A290>",
+        "_predict": "<function DQNPolicy._predict at 0x000002BC8E39A320>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x000002BC8E39A3B0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x000002BC8E39A440>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x000002BC8E3AABC0>"
+    },
+    "verbose": 1,
+    "policy_kwargs": {},
+    "num_timesteps": 50176,
+    "_total_timesteps": 50000,
+    "_num_timesteps_at_start": 0,
+    "seed": null,
+    "action_noise": null,
+    "start_time": 1713559494965558700,
+    "learning_rate": 0.003,
+    "tensorboard_log": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAJmLAMCI3Ei69RMrPGnzU72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAG9LAMCZgUi+vW25O+bidD6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+    },
+    "_episode_num": 869,
+    "use_sde": false,
+    "sde_sample_freq": -1,
+    "_current_progress_remaining": -0.0035199999999999676,
+    "_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": 24704,
+    "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": 100000,
+    "batch_size": 64,
+    "learning_starts": 1000,
+    "tau": 1.0,
+    "gamma": 0.99,
+    "gradient_steps": 128,
+    "optimize_memory_usage": false,
+    "replay_buffer_class": {
+        ":type:": "<class 'abc.ABCMeta'>",
+        ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==",
+        "__module__": "stable_baselines3.common.buffers",
+        "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}",
+        "__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 0x000002BC8E0B3130>",
+        "add": "<function ReplayBuffer.add at 0x000002BC8E0B31C0>",
+        "sample": "<function ReplayBuffer.sample at 0x000002BC8E0B3250>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x000002BC8E0B32E0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x000002BC8E0B3370>)>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x000002BC8B8AD700>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYgAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RNAAFoAIwSVHJhaW5GcmVxdWVuY3lVbml0lJOUjARzdGVwlIWUUpSGlIGULg=="
+    },
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.04,
+    "exploration_fraction": 0.16,
+    "target_update_interval": 10,
+    "_n_calls": 50176,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.04,
+    "lr_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "gAWVlAIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMf2Q6XGpvbmFoXERvY3VtZW50c1xVbmlcV0lcMDNfQmFjaGVsb3JhcmJlaXRcSW1wbGVtZW50YXRpb25cR3ltbmFzaXVtXC5jb25kYVxsaWJcc2l0ZS1wYWNrYWdlc1xzdGFibGVfYmFzZWxpbmVzM1xjb21tb25cdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UaAx1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoHn2UfZQoaBZoDYwMX19xdWFsbmFtZV9flIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5SMD19fYW5ub3RhdGlvbnNfX5R9lIwOX19rd2RlZmF1bHRzX1+UTowMX19kZWZhdWx0c19flE6MCl9fbW9kdWxlX1+UaBeMB19fZG9jX1+UTowLX19jbG9zdXJlX1+UaACMCl9tYWtlX2NlbGyUk5RHP2iTdLxqfvqFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMC4="
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
+    }
+}

DQN-CartPole-v1_2/policy.optimizer.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7eabc7e1b52aa69d4470e2867fed59eee29cd2e782d8c770e1c148e0170803
+size 42144

DQN-CartPole-v1_2/policy.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:596b5430251fa9990b16447e87194758b22b54f74012ec1ccdc36d331ae913df
+size 41266

DQN-CartPole-v1_2/pytorch_variables.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4dde0c1ad63b7740276006a06cc491b21b407ea6c889928c223ec77ddad79f
+size 864

DQN-CartPole-v1_2/system_info.txt

@@ -0,0 +1,8 @@
+- OS: Windows-10-10.0.22631-SP0 10.0.22631
+- Python: 3.10.14
+- Stable-Baselines3: 2.3.0
+- PyTorch: 2.2.2+cpu
+- GPU Enabled: False
+- Numpy: 1.26.4
+- Cloudpickle: 3.0.0
+- Gymnasium: 0.29.1

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: 17.70 +/- 1.35
+      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 0x000002BC8E39A0E0>", "_build": "<function DQNPolicy._build at 0x000002BC8E39A170>", "make_q_net": "<function DQNPolicy.make_q_net at 0x000002BC8E39A200>", "forward": "<function DQNPolicy.forward at 0x000002BC8E39A290>", "_predict": "<function DQNPolicy._predict at 0x000002BC8E39A320>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x000002BC8E39A3B0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x000002BC8E39A440>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002BC8E3AABC0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 50176, "_total_timesteps": 50000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1713559494965558700, "learning_rate": 0.003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAJmLAMCI3Ei69RMrPGnzU72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAG9LAMCZgUi+vW25O+bidD6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_episode_num": 869, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.0035199999999999676, "_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": 24704, "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": 100000, "batch_size": 64, "learning_starts": 1000, "tau": 1.0, "gamma": 0.99, "gradient_steps": 128, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwMUmVwbGF5QnVmZmVylJOULg==", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observations': <class 'numpy.ndarray'>, 'next_observations': <class 'numpy.ndarray'>, 'actions': <class 'numpy.ndarray'>, 'rewards': <class 'numpy.ndarray'>, 'dones': <class 'numpy.ndarray'>, 'timeouts': <class 'numpy.ndarray'>}", "__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 0x000002BC8E0B3130>", "add": "<function ReplayBuffer.add at 0x000002BC8E0B31C0>", "sample": "<function ReplayBuffer.sample at 0x000002BC8E0B3250>", "_get_samples": "<function ReplayBuffer._get_samples at 0x000002BC8E0B32E0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x000002BC8E0B3370>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000002BC8B8AD700>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYgAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RNAAFoAIwSVHJhaW5GcmVxdWVuY3lVbml0lJOUjARzdGVwlIWUUpSGlIGULg=="}, "use_sde_at_warmup": false, "exploration_initial_eps": 1.0, "exploration_final_eps": 0.04, "exploration_fraction": 0.16, "target_update_interval": 10, "_n_calls": 50176, "max_grad_norm": 10, "exploration_rate": 0.04, "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": "Windows-10-10.0.22631-SP0 10.0.22631", "Python": "3.10.14", "Stable-Baselines3": "2.3.0", "PyTorch": "2.2.2+cpu", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}

results.json

@@ -0,0 +1 @@
+{"mean_reward": 17.7, "std_reward": 1.345362404707371, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-19T23:06:22.658874"}