Initial commit

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 0x17aadb060>", "_build": "<function DQNPolicy._build at 0x17aadb100>", "make_q_net": "<function DQNPolicy.make_q_net at 0x17aadb1a0>", "forward": "<function DQNPolicy.forward at 0x17aadb240>", "_predict": "<function DQNPolicy._predict at 0x17aadb2e0>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x17aadb380>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x17aadb420>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17aaf2c80>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "low_repr": "[-1.2  -0.07]", "high_repr": "[0.6  0.07]", "_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, "buffer_size": 10000, "batch_size": 64, "learning_starts": 1000, "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 0x17a5e5a80>", "add": "<function ReplayBuffer.add at 0x17a5e5bc0>", "sample": "<function ReplayBuffer.sample at 0x17a5e5c60>", "_get_samples": "<function ReplayBuffer._get_samples at 0x17a5e5d00>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x17a5e5da0>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x17a5ec580>"}, "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": 0.02, "exploration_fraction": 0.1, "target_update_interval": 500, "_n_calls": 0, "max_grad_norm": 10, "exploration_rate": 0.0, "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 21:53:18 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T6000", "Python": "3.11.5", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.2", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}
+{"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 0x28e4c1800>", "_build": "<function DQNPolicy._build at 0x28e4c18a0>", "make_q_net": "<function DQNPolicy.make_q_net at 0x28e4c1940>", "forward": "<function DQNPolicy.forward at 0x28e4c19e0>", "_predict": "<function DQNPolicy._predict at 0x28e4c1a80>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x28e4c1b20>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x28e4c1bc0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x28e4bd800>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 10000000, "_total_timesteps": 10000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1704648812565295000, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAKxi8L4AAAAAkjj3vgAAAABO7+e+AAAAAFJzDL8AAAAAlGwIvwAAAADaytq+AAAAAFoc6L4AAAAAtFEKvwAAAABW0f6+AAAAALcx1L4AAAAA/z78vgAAAADawAu/AAAAAM0a/74AAAAAwc3svgAAAACn2Oq+AAAAAKkYz74AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAF7vNL+T0527Kdo0vyrcmLvQGTK/u+W8u3qDNb/lP4e7aK82v2pWRbsMbDa/+ENVu1vrKr/Xrha7FIk0v5U20rtN1Ti/OFAEu7qFMr8aBtK7+Ms1v4Xcn7s1YC+/gWrsu6iEJr8wpEe745Myv7znqLvpQyq/BqwWuylTOL/ATB67lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="}, "_episode_num": 50000, "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": 156235, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True]", "bounded_above": "[ True  True]", "_shape": [2], "low": "[-1.2  -0.07]", "high": "[0.6  0.07]", "low_repr": "[-1.2  -0.07]", "high_repr": "[0.6  0.07]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "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", "n": "3", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 16, "buffer_size": 10000, "batch_size": 64, "learning_starts": 1000, "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 0x28e193e20>", "add": "<function ReplayBuffer.add at 0x28e193f60>", "sample": "<function ReplayBuffer.sample at 0x28e1b4040>", "_get_samples": "<function ReplayBuffer._get_samples at 0x28e1b40e0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x28e1b4180>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x28c483d40>"}, "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": 0.02, "exploration_fraction": 0.1, "target_update_interval": 500, "_n_calls": 625000, "max_grad_norm": 10, "exploration_rate": 0.02, "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 21:53:18 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T6000", "Python": "3.11.5", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.2", "GPU Enabled": "False", "Numpy": "1.26.2", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1"}}

model_dqn_mount_car.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66e148016a9545c5b23cedd46bd186eea18c90c7ecdc1702dc7ab7ff1d3b2eba
-size 53153
+oid sha256:2a5f608c1e67d7ac38350b242727e9cb03ddd844935b49c3650c77c3c682de7d
+size 99379

model_dqn_mount_car/data

@@ -5,37 +5,52 @@
         "__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 0x17aadb060>",
-        "_build": "<function DQNPolicy._build at 0x17aadb100>",
-        "make_q_net": "<function DQNPolicy.make_q_net at 0x17aadb1a0>",
-        "forward": "<function DQNPolicy.forward at 0x17aadb240>",
-        "_predict": "<function DQNPolicy._predict at 0x17aadb2e0>",
-        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x17aadb380>",
-        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x17aadb420>",
+        "__init__": "<function DQNPolicy.__init__ at 0x28e4c1800>",
+        "_build": "<function DQNPolicy._build at 0x28e4c18a0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x28e4c1940>",
+        "forward": "<function DQNPolicy.forward at 0x28e4c19e0>",
+        "_predict": "<function DQNPolicy._predict at 0x28e4c1a80>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x28e4c1b20>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x28e4c1bc0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x17aaf2c80>"
+        "_abc_impl": "<_abc._abc_data object at 0x28e4bd800>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 10000000,
+    "_total_timesteps": 10000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1704648812565295000,
     "learning_rate": 0.001,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": null,
-    "_last_original_obs": null,
-    "_episode_num": 0,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAKxi8L4AAAAAkjj3vgAAAABO7+e+AAAAAFJzDL8AAAAAlGwIvwAAAADaytq+AAAAAFoc6L4AAAAAtFEKvwAAAABW0f6+AAAAALcx1L4AAAAA/z78vgAAAADawAu/AAAAAM0a/74AAAAAwc3svgAAAACn2Oq+AAAAAKkYz74AAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWV9QAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJaAAAAAAAAAAF7vNL+T0527Kdo0vyrcmLvQGTK/u+W8u3qDNb/lP4e7aK82v2pWRbsMbDa/+ENVu1vrKr/Xrha7FIk0v5U20rtN1Ti/OFAEu7qFMr8aBtK7+Ms1v4Xcn7s1YC+/gWrsu6iEJr8wpEe745Myv7znqLvpQyq/BqwWuylTOL/ATB67lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwKGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 50000,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1.0,
+    "_current_progress_remaining": 0.0,
     "_stats_window_size": 100,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 156235,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -53,12 +68,12 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIAwAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "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",
         "n": "3",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
-        "_np_random": null
+        "_np_random": "Generator(PCG64)"
     },
     "n_envs": 16,
     "buffer_size": 10000,
@@ -74,13 +89,13 @@
         "__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 0x17a5e5a80>",
-        "add": "<function ReplayBuffer.add at 0x17a5e5bc0>",
-        "sample": "<function ReplayBuffer.sample at 0x17a5e5c60>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x17a5e5d00>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x17a5e5da0>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x28e193e20>",
+        "add": "<function ReplayBuffer.add at 0x28e193f60>",
+        "sample": "<function ReplayBuffer.sample at 0x28e1b4040>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x28e1b40e0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x28e1b4180>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x17a5ec580>"
+        "_abc_impl": "<_abc._abc_data object at 0x28c483d40>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {
@@ -92,9 +107,9 @@
     "exploration_final_eps": 0.02,
     "exploration_fraction": 0.1,
     "target_update_interval": 500,
-    "_n_calls": 0,
+    "_n_calls": 625000,
     "max_grad_norm": 10,
-    "exploration_rate": 0.0,
+    "exploration_rate": 0.02,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

model_dqn_mount_car/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be7683cfd1918f9733a8d8750f796e1ec7a0a5eed0aab2a7f5d390c43fff2e9
-size 1120
+oid sha256:2beec9a2307a9caad544bdd7cb7051f6d2c252e1abd28edd391134a1b0189588
+size 41632

model_dqn_mount_car/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b67f0355897a4cbfdad70535600971fd55521754fd148ead68fc5dcce218a9
+oid sha256:cb1b14cc2d60f6cc268f28336b51073856f1039f465042e7070d4c93031790eb
 size 40754

results.json

@@ -1 +1 @@
-{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-07T17:49:36.140616"}
+{"mean_reward": -200.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-07T18:47:25.402642"}