Push to Hub

DQN-CartPole-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8993cfa3d824c7f46f9dd3413592934dd53664db052128dbf498834111ec35d
-size 1108111
+oid sha256:fb3f3fdb8e0b2be72cc79a8dc9708652b40fd9ee547ddef02877c3a2a4002426
+size 1108374

DQN-CartPole-v1/data

@@ -5,15 +5,15 @@
         "__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 0x7d0a36d91c60>",
-        "_build": "<function DQNPolicy._build at 0x7d0a36d91cf0>",
-        "make_q_net": "<function DQNPolicy.make_q_net at 0x7d0a36d91d80>",
-        "forward": "<function DQNPolicy.forward at 0x7d0a36d91e10>",
-        "_predict": "<function DQNPolicy._predict at 0x7d0a36d91ea0>",
-        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7d0a36d91f30>",
-        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7d0a36d91fc0>",
+        "__init__": "<function DQNPolicy.__init__ at 0x791a617ede10>",
+        "_build": "<function DQNPolicy._build at 0x791a617edea0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x791a617edf30>",
+        "forward": "<function DQNPolicy.forward at 0x791a617edfc0>",
+        "_predict": "<function DQNPolicy._predict at 0x791a617ee050>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x791a617ee0e0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x791a617ee170>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d0a36d99f80>"
+        "_abc_impl": "<_abc._abc_data object at 0x791a617ebe40>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -30,12 +30,12 @@
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1698319130950854755,
+    "start_time": 1698322213186748147,
     "learning_rate": 0.0001,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAIDHHT3lbEg+8H1oPJ4ijb6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAHzTiT4Vyxs+mtQCvdzqRz6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
@@ -43,16 +43,16 @@
     },
     "_last_original_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAIu2HT1w91M6Il1kPF5oTjyUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
+        ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAFJGhj4wkrE+lUf3vE7Es72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"
     },
-    "_episode_num": 3901,
+    "_episode_num": 3595,
     "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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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
@@ -76,7 +76,7 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "n": "2",
         "start": "0",
         "_shape": [],
@@ -97,13 +97,13 @@
         "__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 0x7d0a36d76050>",
-        "add": "<function ReplayBuffer.add at 0x7d0a36d760e0>",
-        "sample": "<function ReplayBuffer.sample at 0x7d0a36d76170>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7d0a36d76200>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7d0a36d76290>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x791a617c6200>",
+        "add": "<function ReplayBuffer.add at 0x791a617c6290>",
+        "sample": "<function ReplayBuffer.sample at 0x791a617c6320>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x791a617c63b0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x791a617c6440>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d0a36d67980>"
+        "_abc_impl": "<_abc._abc_data object at 0x791a617cd9c0>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

DQN-CartPole-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cbd438dbc1caa7e23a016b05ac334b813fae37c32081fd69202cd1bb5512cff
-size 545952
+oid sha256:a79edb5197d98ad3164c4e61d9dec47e012e13e42d7fb74bc33c2980a28beb83
+size 546080

DQN-CartPole-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b6df65b831bd56877cd6d725ffb81a965221811746a89ce570a8982597d9a7
-size 545074
+oid sha256:d3ee901395acb609a77d55fa464c945eb22d07fd98654059dee3d008ce86aefd
+size 545202

DQN-CartPole-v1/system_info.txt

@@ -2,7 +2,7 @@
 - Python: 3.10.12
 - Stable-Baselines3: 2.2.0a8
 - PyTorch: 2.1.0+cu118
-- GPU Enabled: False
+- GPU Enabled: True
 - Numpy: 1.23.5
 - Cloudpickle: 2.2.1
 - Gymnasium: 0.29.1

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 199.10 +/- 30.59
+      value: 213.40 +/- 49.12
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +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 0x7d0a36d91c60>", "_build": "<function DQNPolicy._build at 0x7d0a36d91cf0>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7d0a36d91d80>", "forward": "<function DQNPolicy.forward at 0x7d0a36d91e10>", "_predict": "<function DQNPolicy._predict at 0x7d0a36d91ea0>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7d0a36d91f30>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7d0a36d91fc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d0a36d99f80>"}, "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": 1698319130950854755, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAIDHHT3lbEg+8H1oPJ4ijb6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAIu2HT1w91M6Il1kPF5oTjyUjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_episode_num": 3901, "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", "__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 0x7d0a36d76050>", "add": "<function ReplayBuffer.add at 0x7d0a36d760e0>", "sample": "<function ReplayBuffer.sample at 0x7d0a36d76170>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7d0a36d76200>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7d0a36d76290>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d0a36d67980>"}, "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": "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": "2.2.0a8", "PyTorch": "2.1.0+cu118", "GPU Enabled": "False", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}
+{"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 0x791a617ede10>", "_build": "<function DQNPolicy._build at 0x791a617edea0>", "make_q_net": "<function DQNPolicy.make_q_net at 0x791a617edf30>", "forward": "<function DQNPolicy.forward at 0x791a617edfc0>", "_predict": "<function DQNPolicy._predict at 0x791a617ee050>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x791a617ee0e0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x791a617ee170>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x791a617ebe40>"}, "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": 1698322213186748147, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAHzTiT4Vyxs+mtQCvdzqRz6UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVhQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAFJGhj4wkrE+lUf3vE7Es72UjAVudW1weZSMBWR0eXBllJOUjAJmNJSJiIeUUpQoSwOMATyUTk5OSv////9K/////0sAdJRiSwFLBIaUjAFDlHSUUpQu"}, "_episode_num": 3595, "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:": "gAWVEAIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lGgFk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAABAQEBlGgHjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKUjA1ib3VuZGVkX2Fib3ZllGgQKJYEAAAAAAAAAAEBAQGUaBRLBIWUaBh0lFKUjAZfc2hhcGWUSwSFlIwDbG93lGgQKJYQAAAAAAAAAJqZmcD//3//UHfWvv//f/+UaApLBIWUaBh0lFKUjARoaWdolGgQKJYQAAAAAAAAAJqZmUD//39/UHfWPv//f3+UaApLBIWUaBh0lFKUjAhsb3dfcmVwcpSMPVstNC44MDAwMDAyZSswMCAtMy40MDI4MjM1ZSszOCAtNC4xODg3OTAzZS0wMSAtMy40MDI4MjM1ZSszOF2UjAloaWdoX3JlcHKUjDlbNC44MDAwMDAyZSswMCAzLjQwMjgyMzVlKzM4IDQuMTg4NzkwM2UtMDEgMy40MDI4MjM1ZSszOF2UjApfbnBfcmFuZG9tlE51Yi4=", "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", "__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 0x791a617c6200>", "add": "<function ReplayBuffer.add at 0x791a617c6290>", "sample": "<function ReplayBuffer.sample at 0x791a617c6320>", "_get_samples": "<function ReplayBuffer._get_samples at 0x791a617c63b0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x791a617c6440>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x791a617cd9c0>"}, "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": "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": "2.2.0a8", "PyTorch": "2.1.0+cu118", "GPU Enabled": "True", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": 199.1, "std_reward": 30.589050328508076, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-26T11:23:56.278969"}
+{"mean_reward": 213.4, "std_reward": 49.116595973255315, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-26T12:13:26.299419"}