Push to Hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 75.19 +/- 100.03
+      value: -249.17 +/- 111.44
       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 0x7d0f6db303a0>", "_build": "<function DQNPolicy._build at 0x7d0f6db30430>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7d0f6db304c0>", "forward": "<function DQNPolicy.forward at 0x7d0f6db30550>", "_predict": "<function DQNPolicy._predict at 0x7d0f6db305e0>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7d0f6db30670>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7d0f6db30700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d0f6db34500>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709540420393297656, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGZH8D0MfoQ+AoYWPnz6V74DCls8FDEjuwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAFpF7T0U7IY+VBgZPkIygb5MFF081ZW1ugAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_episode_num": 655, "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, "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 0x7d0f6db14820>", "add": "<function ReplayBuffer.add at 0x7d0f6db148b0>", "sample": "<function ReplayBuffer.sample at 0x7d0f6db14940>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7d0f6db149d0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7d0f6db14a60>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d0f6dc3b800>"}, "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": 0.1, "exploration_fraction": 0.1, "target_update_interval": 250, "_n_calls": 100000, "max_grad_norm": 10, "exploration_rate": 0.1, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWVxQEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwQX19nZW5lcmF0b3JfY3RvcpSTlIwFUENHNjSUaB+MFF9fYml0X2dlbmVyYXRvcl9jdG9ylJOUhpRSlH2UKIwNYml0X2dlbmVyYXRvcpSMBVBDRzY0lIwFc3RhdGWUfZQoaCqKEM0WtMTaha2wDqNppsgJIiOMA2luY5SKEO3tfNn7rtT/bszUWgMkI1t1jApoYXNfdWludDMylEsAjAh1aW50ZWdlcpSKBYyPk8MAdWJ1Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "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-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023", "Python": "3.10.13", "Stable-Baselines3": "2.1.0", "PyTorch": "2.1.2+cpu", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.0", "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 0x7c12c0d72c20>", "_build": "<function DQNPolicy._build at 0x7c12c0d72cb0>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7c12c0d72d40>", "forward": "<function DQNPolicy.forward at 0x7c12c0d72dd0>", "_predict": "<function DQNPolicy._predict at 0x7c12c0d72e60>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7c12c0d72ef0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7c12c0d72f80>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c12c0d896c0>"}, "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": 0.0001, "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:": "gAWVZgIAAAAAAACMFGd5bW5hc2l1bS5zcGFjZXMuYm94lIwDQm94lJOUKYGUfZQojAVkdHlwZZSMBW51bXB5lIwFZHR5cGWUk5SMAmY0lImIh5RSlChLA4wBPJROTk5K/////0r/////SwB0lGKMDWJvdW5kZWRfYmVsb3eUjBJudW1weS5jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWCAAAAAAAAAABAQEBAQEBAZRoCIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksIhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoESiWCAAAAAAAAAABAQEBAQEBAZRoFUsIhZRoGXSUUpSMBl9zaGFwZZRLCIWUjANsb3eUaBEoliAAAAAAAAAAAADAvwAAwL8AAKDAAACgwNsPScAAAKDAAAAAgAAAAICUaAtLCIWUaBl0lFKUjARoaWdolGgRKJYgAAAAAAAAAAAAwD8AAMA/AACgQAAAoEDbD0lAAACgQAAAgD8AAIA/lGgLSwiFlGgZdJRSlIwIbG93X3JlcHKUjFNbLTEuNSAgICAgICAtMS41ICAgICAgIC01LiAgICAgICAgLTUuICAgICAgICAtMy4xNDE1OTI3IC01LgogLTAuICAgICAgICAtMC4gICAgICAgXZSMCWhpZ2hfcmVwcpSMS1sxLjUgICAgICAgMS41ICAgICAgIDUuICAgICAgICA1LiAgICAgICAgMy4xNDE1OTI3IDUuICAgICAgICAxLgogMS4gICAgICAgXZSMCl9ucF9yYW5kb22UTnViLg==", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]", "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.discrete.Discrete'>", ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=", "n": "4", "start": "0", "_shape": [], "dtype": "int64", "_np_random": null}, "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 0x7c12c0ea4160>", "add": "<function ReplayBuffer.add at 0x7c12c0ea41f0>", "sample": "<function ReplayBuffer.sample at 0x7c12c0ea4280>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7c12c0ea4310>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7c12c0ea43a0>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c12c0e8fc00>"}, "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": 0.1, "exploration_fraction": 0.1, "target_update_interval": 250, "_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": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.0+cu121", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}

dqn-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b821988625098a056b83b7c58e8b20f4e3d3f1039e37ac8fb87383047331176f
-size 106508
+oid sha256:01582ac60413dec5922b347a0812b071ea39c377716e275715e753723eb1bbc9
+size 57115

dqn-LunarLander-v2/_stable_baselines3_version

@@ -1 +1 @@
-2.1.0
+2.2.1

dqn-LunarLander-v2/data

@@ -5,52 +5,62 @@
         "__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 0x7d0f6db303a0>",
-        "_build": "<function DQNPolicy._build at 0x7d0f6db30430>",
-        "make_q_net": "<function DQNPolicy.make_q_net at 0x7d0f6db304c0>",
-        "forward": "<function DQNPolicy.forward at 0x7d0f6db30550>",
-        "_predict": "<function DQNPolicy._predict at 0x7d0f6db305e0>",
-        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7d0f6db30670>",
-        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7d0f6db30700>",
+        "__init__": "<function DQNPolicy.__init__ at 0x7c12c0d72c20>",
+        "_build": "<function DQNPolicy._build at 0x7c12c0d72cb0>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7c12c0d72d40>",
+        "forward": "<function DQNPolicy.forward at 0x7c12c0d72dd0>",
+        "_predict": "<function DQNPolicy._predict at 0x7c12c0d72e60>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7c12c0d72ef0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7c12c0d72f80>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d0f6db34500>"
+        "_abc_impl": "<_abc._abc_data object at 0x7c12c0d896c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 100000,
-    "_total_timesteps": 100000,
+    "num_timesteps": 0,
+    "_total_timesteps": 0,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1709540420393297656,
+    "start_time": 0.0,
     "learning_rate": 0.0001,
     "tensorboard_log": null,
-    "_last_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAGZH8D0MfoQ+AoYWPnz6V74DCls8FDEjuwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
-    },
-    "_last_episode_starts": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
-    },
-    "_last_original_obs": {
-        ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAAFpF7T0U7IY+VBgZPkIygb5MFF081ZW1ugAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
-    },
-    "_episode_num": 655,
+    "_last_obs": null,
+    "_last_episode_starts": null,
+    "_last_original_obs": null,
+    "_episode_num": 0,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 0.0,
+    "_current_progress_remaining": 1.0,
     "_stats_window_size": 100,
-    "ep_info_buffer": {
-        ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVJgwAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwHNj/OlfqouMAWyUSzWMAXSUR0BBlRmseXAudX2UKGgGR8CA/I7wrlNlaAdLRmgIR0BBpExIre67dX2UKGgGR8CByDkhA4XGaAdLTmgIR0BBtYffXPJJdX2UKGgGR8B/QF4C6pYLaAdLW2gIR0BBy/Pw/gR9dX2UKGgGR8CG5oTvAoG6aAdLdGgIR0BB5tWU8mrsdX2UKGgGR8CDkBC79Q40aAdLj2gIR0BCC/ukUKzBdX2UKGgGR8B6pZTAFgUlaAdLT2gIR0BCHdNFjNILdX2UKGgGR8B9PqvIOpbVaAdLUGgIR0BCL5+YtxuLdX2UKGgGR8CQGQ+pwS8KaAdLj2gIR0BCU1u76Hj7dX2UKGgGR8CRuN4mCyyEaAdL4WgIR0BCjn8jzI3jdX2UKGgGR8B7VzRTjvNNaAdLUWgIR0BCobqptJnQdX2UKGgGR8CJFMkZ75VPaAdLfmgIR0BCv5kCmuTzdX2UKGgGR8CGSvglWwNcaAdLfWgIR0BC3OrIYFaCdX2UKGgGR8CB6gXSBshxaAdLT2gIR0BC7jin5zo2dX2UKGgGR8CTQbBe5WilaAdL2GgIR0BDJPwVj7Q+dX2UKGgGR8CEdeunuRcNaAdLY2gIR0BDPliKBNEgdX2UKGgGR8CCs6ydFvycaAdLVWgIR0BDUcjZ+QU6dX2UKGgGR8CRnUme18b8aAdLmGgIR0BDdzjFQ2uQdX2UKGgGR8CQL1oK2KEWaAdLnGgIR0BDnqjzqbBodX2UKGgGR8CA7dBrN4Z/aAdLSWgIR0BDrxLTQVsUdX2UKGgGR8B/f7eZXuE3aAdLY2gIR0BDxrt/nW8RdX2UKGgGR8CB+8IzFdcCaAdLhWgIR0BD5gUcn3L3dX2UKGgGR8CSJ8+MZP2xaAdL3GgIR0BEH+9SMtK7dX2UKGgGR8CMrgeAd4mkaAdLg2gIR0BEQcdYGMXKdX2UKGgGR8CGap6qKgqWaAdLemgIR0BEXf1pTMq0dX2UKGgGR8CGWwUL2HtXaAdLuGgIR0BEiyteUpuudX2UKGgGR8Bw3rNPgvUSaAdLZWgIR0BEoZmyxA0LdX2UKGgGR8CBcy+fywwCaAdNJwFoCEdARPOrS3LFGXV9lChoBkfAgCSGHpKSPmgHTWsBaAhHQEVaKmbb1yx1fZQoaAZHwHVrFpoK2KFoB00HAmgIR0BGDL5ZbILgdX2UKGgGR8BWgKPjn3cpaAdNRAFoCEdARmSItUXHinV9lChoBkfAWorIkqtoz2gHTegDaAhHQEfV9aUzKtB1fZQoaAZHQGQArBCUorpoB02/AmgIR0BJEIR7JGONdX2UKGgGR8BaFqxHG0eEaAdN6ANoCEdASv1GmUGFBnV9lChoBkfAQ+mpuMuOCGgHTegDaAhHQEy1iw0O3Dx1fZQoaAZHwG02I5YHPeJoB0v6aAhHQEz2XJo0ygx1fZQoaAZHwGH2+XZ5AyFoB03oA2gIR0BOci3ocJdCdX2UKGgGR8BjN0KzAvcraAdN6ANoCEdAUAoI0IkZ8HV9lChoBkfAYQNSZ0CA+mgHTegDaAhHQFDo7BfrrxB1fZQoaAZHwGDiuWKMvRJoB03oA2gIR0BR3NZ3cHnmdX2UKGgGR8BlTi3/giu/aAdN6ANoCEdAUv/WK/EfknV9lChoBkfAYbLhuO0b+GgHTegDaAhHQFP2++ueSSx1fZQoaAZHwGSrKXfIjnpoB03oA2gIR0BU2o46wMYudX2UKGgGR8BM+k92X9iuaAdN6ANoCEdAVbOVgQYk3XV9lChoBkfAOR3gDRtxdmgHTegDaAhHQFbcfA9FF2F1fZQoaAZHwFWHZiuuA7RoB02SAmgIR0BXXlWbPQfIdX2UKGgGR8BQrtdu5z5oaAdN6ANoCEdAWJeNAC4jKXV9lChoBkfAVpiee4Cp32gHTegDaAhHQFlbpQDV6NV1fZQoaAZHwERwt4A0bcZoB02KAmgIR0BZ0ZKJ2t+1dX2UKGgGR0BV9xHPNVzZaAdNkQNoCEdAWqAKc/dIoXV9lChoBkfAOVR5TqB3A2gHTegDaAhHQFt6801qFh51fZQoaAZHwF/zgJ1JUYNoB021A2gIR0BcZatozvZzdX2UKGgGR8A2nAZKnNxEaAdNVQJoCEdAXNrFVDKHPHV9lChoBkdAblBqkdmxuGgHTUgCaAhHQF1KSyMUAT91fZQoaAZHwEx0S6DoQnRoB02+AmgIR0Bd29Gqgh8qdX2UKGgGR8BV1k/B3zMBaAdNhwJoCEdAXlLb0voNeHV9lChoBkfAVmejXWe6I2gHTRICaAhHQF61vLX+VC51fZQoaAZHQD5cB6rvLHNoB03oA2gIR0BfwwP3BYV7dX2UKGgGR0BjvLjYI0IkaAdNRwNoCEdAYDvCjUNKAnV9lChoBkfAVOxAu7HyVmgHTVcCaAhHQGB84Lsrupl1fZQoaAZHQDSgUHpr1uloB03oA2gIR0Bg8Blg+hXbdX2UKGgGR8Awos9B8hLXaAdNMgFoCEdAYQSEkB0ZFXV9lChoBkdAY6zh5xBE8mgHTakCaAhHQGFEz6zmfXh1fZQoaAZHQF/HjgydnTRoB00uA2gIR0BhpK+SKWLQdX2UKGgGR8BJZlDv3JxOaAdN/wFoCEdAYdSSLZSNwXV9lChoBkfAVzbkT6BRRGgHTb0BaAhHQGH+8ohIOH51fZQoaAZHv+vMcIZ62ORoB03fAWgIR0BiKUPhAGB4dX2UKGgGR0BnJAHTqjagaAdNOAJoCEdAYmQDr7fpEHV9lChoBkfAEVcjJMg2ZWgHTb0BaAhHQGKGbPyCnP51fZQoaAZHQBLJ79hqj8FoB026AWgIR0Biqis0YTCcdX2UKGgGR8BgvfF3pwCKaAdNVwJoCEdAYuN67/XGwXV9lChoBkdAaolZGrjo6mgHTfwBaAhHQGMZfqgRK6F1fZQoaAZHwFjnWattALRoB03jAWgIR0BjR3bh3qzJdX2UKGgGR8BKlTw+dK/VaAdNlgFoCEdAY2pj3Ehq03V9lChoBkdAZLtVMEidKGgHTSACaAhHQGOg41pCa7V1fZQoaAZHQG2XthuwX69oB03FAWgIR0BjyRFy7wrldX2UKGgGR8BLpQ22oegdaAdNpgFoCEdAY+zIdU83dnV9lChoBkdAA/j94u9OAWgHTZ8BaAhHQGQPi1Aqur91fZQoaAZHQGcycebNKRNoB02IAmgIR0BkTgdXDFZQdX2UKGgGR0BoNDbL2YfGaAdNFgNoCEdAZKwp4KQaJnV9lChoBkfAP5eEqUeMh2gHTU8BaAhHQGTFHJT2nKp1fZQoaAZHwEvLYzSCvoxoB012AWgIR0Bk4o+GGmDUdX2UKGgGR8Av0UpNKyv+aAdLlWgIR0Bk6+inHeabdX2UKGgGR0BlyF2FFlTWaAdNuwFoCEdAZRAziS7oS3V9lChoBkdAZ4av/R3NcGgHTRgCaAhHQGVBIp6QeV91fZQoaAZHQGVe2mYSg5BoB03JAmgIR0BljJbjcVQAdX2UKGgGR0AwmxxT850baAdNtQFoCEdAZa1BzFMqSXV9lChoBkfAMQZj2Bas62gHTToBaAhHQGXElI3BHkN1fZQoaAZHwEd5jDsMRYloB03SAWgIR0Bl7orFwT/RdX2UKGgGR0Bmy6b+cYqHaAdNqgJoCEdAZjlgdfb9InV9lChoBkfAPhPnnuAqeGgHTfQBaAhHQGZi80+C9RJ1fZQoaAZHQDM4M7U5MlFoB00oAWgIR0Bmd+tnwob5dX2UKGgGR0BnT+FHrhR7aAdN2gJoCEdAZskz0HyEtnV9lChoBkdAafqRSxZ+yGgHTa8BaAhHQGbrBr30wrV1fZQoaAZHwETtDhtLteFoB02DAWgIR0BnCt8ma6SUdX2UKGgGR8AuTzXBguyvaAdL42gIR0BnGguyu6mPdX2UKGgGR0BiijvE0iyIaAdN3gJoCEdAZ3NA0Kqn33V9lChoBkfAMYBHXmNipmgHTUYBaAhHQGeO8baRISV1fZQoaAZHQGkrhDPWxyJoB038AWgIR0Bnw7gIhQnAdX2UKGgGR8BLAKSHM2WIaAdNPgFoCEdAZ9yqNp/PPnVlLg=="
+    "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  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
+        "_shape": [
+            8
+        ],
+        "low": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
+        "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]",
+        "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
+        "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]",
+        "_np_random": null
     },
-    "ep_success_buffer": {
-        ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    "action_space": {
+        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
+        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": null
     },
-    "_n_updates": 12500,
+    "n_envs": 1,
     "buffer_size": 1000000,
     "batch_size": 32,
     "learning_starts": 50000,
@@ -62,14 +72,15 @@
         ":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 0x7d0f6db14820>",
-        "add": "<function ReplayBuffer.add at 0x7d0f6db148b0>",
-        "sample": "<function ReplayBuffer.sample at 0x7d0f6db14940>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7d0f6db149d0>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7d0f6db14a60>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7c12c0ea4160>",
+        "add": "<function ReplayBuffer.add at 0x7c12c0ea41f0>",
+        "sample": "<function ReplayBuffer.sample at 0x7c12c0ea4280>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7c12c0ea4310>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7c12c0ea43a0>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7d0f6dc3b800>"
+        "_abc_impl": "<_abc._abc_data object at 0x7c12c0e8fc00>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {
@@ -81,42 +92,17 @@
     "exploration_final_eps": 0.1,
     "exploration_fraction": 0.1,
     "target_update_interval": 250,
-    "_n_calls": 100000,
+    "_n_calls": 0,
     "max_grad_norm": 10,
-    "exploration_rate": 0.1,
-    "observation_space": {
-        ":type:": "<class 'gymnasium.spaces.box.Box'>",
-        ":serialized:": "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",
-        "dtype": "float32",
-        "bounded_below": "[ True  True  True  True  True  True  True  True]",
-        "bounded_above": "[ True  True  True  True  True  True  True  True]",
-        "_shape": [
-            8
-        ],
-        "low": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
-        "high": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]",
-        "low_repr": "[-1.5       -1.5       -5.        -5.        -3.1415927 -5.\n -0.        -0.       ]",
-        "high_repr": "[1.5       1.5       5.        5.        3.1415927 5.        1.\n 1.       ]",
-        "_np_random": null
-    },
-    "action_space": {
-        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "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",
-        "n": "4",
-        "start": "0",
-        "_shape": [],
-        "dtype": "int64",
-        "_np_random": "Generator(PCG64)"
-    },
-    "n_envs": 1,
+    "exploration_rate": 0.0,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8aNuLrHEMthZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
     },
     "batch_norm_stats": [],
     "batch_norm_stats_target": [],
     "exploration_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     }
 }

dqn-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf959ac5391f26909a187f61e43fbf0cbb64621c546e88ff615342fa08a211e
-size 45216
+oid sha256:9abc378f787a2758cb67761654e5cef6333ec995cbb6987a3bfb5bdc57e986ce
+size 1120

dqn-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6253a81777b16ae30e99659e5958d71cc9f418be4e1e5ad3cb9db41c40d0e611
+oid sha256:d59c157a8c160d36c53022ecf24dc98708d274ea118083017b87978a9037c472
 size 44338

dqn-LunarLander-v2/system_info.txt

@@ -1,9 +1,9 @@
-- OS: Linux-5.15.133+-x86_64-with-glibc2.31 # 1 SMP Tue Dec 19 13:14:11 UTC 2023
-- Python: 3.10.13
-- Stable-Baselines3: 2.1.0
-- PyTorch: 2.1.2+cpu
+- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
+- Python: 3.10.12
+- Stable-Baselines3: 2.2.1
+- PyTorch: 2.1.0+cu121
 - GPU Enabled: False
-- Numpy: 1.26.4
+- Numpy: 1.25.2
 - Cloudpickle: 2.2.1
-- Gymnasium: 0.29.0
-- OpenAI Gym: 0.26.2
+- Gymnasium: 0.29.1
+- OpenAI Gym: 0.25.2

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff849d502541544eca96ce26d9fee4e170d2054274ef02e9f12e50bcbadee21
-size 157380
+oid sha256:40a4df5a4d337b605583be1c4f5768ded9035585e1e14e5981d4fbcf255bf15b
+size 142014

results.json

@@ -1 +1 @@
-{"mean_reward": 75.19120506179533, "std_reward": 100.03434697117845, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T08:54:45.710929"}
+{"mean_reward": -249.17178186802192, "std_reward": 111.4377198808497, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T11:18:16.926725"}