Push to Hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -249.17 +/- 111.44
+      value: 41.68 +/- 30.81
       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 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:": "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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:": "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8aNuLrHEMthZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "exploration_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVZQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLBEsTQyhkAXwAGACIAWsEcgiIAFMAiAJkAXwAGACIAIgCGAAUAIgBGwAXAFMAlE5LAYaUKYwScHJvZ3Jlc3NfcmVtYWluaW5nlIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwEZnVuY5RLcUMGDAEEARgClIwDZW5klIwMZW5kX2ZyYWN0aW9ulIwFc3RhcnSUh5QpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxJL3Vzci9sb2NhbC9saWIvcHl0aG9uMy4xMC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlGgdKVKUaB0pUpSHlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoI32UfZQoaBhoDYwMX19xdWFsbmFtZV9flIwbZ2V0X2xpbmVhcl9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UKGgKjAhidWlsdGluc5SMBWZsb2F0lJOUjAZyZXR1cm6UaC91jA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGYwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/uZmZmZmZmoWUUpRoN0c/uZmZmZmZmoWUUpRoN0c/8AAAAAAAAIWUUpSHlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "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"}}
+{"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 0x7f3e88af11f0>", "_build": "<function DQNPolicy._build at 0x7f3e88af1280>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7f3e88af1310>", "forward": "<function DQNPolicy.forward at 0x7f3e88af13a0>", "_predict": "<function DQNPolicy._predict at 0x7f3e88af1430>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f3e88af14c0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f3e88af1550>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3e88e829c0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 100000, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1709585141267487266, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABpKAb0wJQc/5ioEPiozir3camk9oXilOwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABqWBr2tiAc/2TcUPkF/sb0fYmg9Y9aGPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="}, "_episode_num": 609, "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 0x7f3e88ac9280>", "add": "<function ReplayBuffer.add at 0x7f3e88ac9310>", "sample": "<function ReplayBuffer.sample at 0x7f3e88ac93a0>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7f3e88ac9430>", "_maybe_cast_dtype": "<staticmethod object at 0x7f3e88b3fa90>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3e88aca100>"}, "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:": "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", "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-6.2.0-1019-azure-x86_64-with-glibc2.36 # 19~22.04.1-Ubuntu SMP Wed Jan 10 22:57:03 UTC 2024", "Python": "3.9.18", "Stable-Baselines3": "2.1.0", "PyTorch": "2.2.1+cpu", "GPU Enabled": "False", "Numpy": "1.26.4", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

dqn-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01582ac60413dec5922b347a0812b071ea39c377716e275715e753723eb1bbc9
-size 57115
+oid sha256:d183bf087a155cce2b6c5e4c27f749661fbd59ce5249caf0d264be1786bfb971
+size 106438

dqn-LunarLander-v2/_stable_baselines3_version

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

dqn-LunarLander-v2/data

@@ -5,62 +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 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>",
+        "__init__": "<function DQNPolicy.__init__ at 0x7f3e88af11f0>",
+        "_build": "<function DQNPolicy._build at 0x7f3e88af1280>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7f3e88af1310>",
+        "forward": "<function DQNPolicy.forward at 0x7f3e88af13a0>",
+        "_predict": "<function DQNPolicy._predict at 0x7f3e88af1430>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7f3e88af14c0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7f3e88af1550>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7c12c0d896c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f3e88e829c0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 100000,
+    "_total_timesteps": 100000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 0.0,
+    "start_time": 1709585141267487266,
     "learning_rate": 0.0001,
     "tensorboard_log": null,
-    "_last_obs": null,
-    "_last_episode_starts": null,
-    "_last_original_obs": null,
-    "_episode_num": 0,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABpKAb0wJQc/5ioEPiozir3camk9oXilOwAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVlQAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYgAAAAAAAAABqWBr2tiAc/2TcUPkF/sb0fYmg9Y9aGPAAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwiGlIwBQ5R0lFKULg=="
+    },
+    "_episode_num": 609,
     "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,
-    "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_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
     },
-    "action_space": {
-        ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
-        "n": "4",
-        "start": "0",
-        "_shape": [],
-        "dtype": "int64",
-        "_np_random": null
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "n_envs": 1,
+    "_n_updates": 12500,
     "buffer_size": 1000000,
     "batch_size": 32,
     "learning_starts": 50000,
@@ -72,15 +62,14 @@
         ":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>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7f3e88ac9280>",
+        "add": "<function ReplayBuffer.add at 0x7f3e88ac9310>",
+        "sample": "<function ReplayBuffer.sample at 0x7f3e88ac93a0>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7f3e88ac9430>",
+        "_maybe_cast_dtype": "<staticmethod object at 0x7f3e88b3fa90>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7c12c0e8fc00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f3e88aca100>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {
@@ -92,17 +81,42 @@
     "exploration_final_eps": 0.1,
     "exploration_fraction": 0.1,
     "target_update_interval": 250,
-    "_n_calls": 0,
+    "_n_calls": 100000,
     "max_grad_norm": 10,
-    "exploration_rate": 0.0,
+    "exploration_rate": 0.1,
+    "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:": "gAWVwwEAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgLjAJpOJSJiIeUUpQoSwNoD05OTkr/////Sv////9LAHSUYowKX25wX3JhbmRvbZSMFG51bXB5LnJhbmRvbS5fcGlja2xllIwQX19nZW5lcmF0b3JfY3RvcpSTlIwFUENHNjSUaB+MFF9fYml0X2dlbmVyYXRvcl9jdG9ylJOUhpRSlH2UKIwNYml0X2dlbmVyYXRvcpSMBVBDRzY0lIwFc3RhdGWUfZQoaCqKEE/bk64y+iUui2SdksNkw36MA2luY5SKEKHQitigrrOcCjYSDR8ZU351jApoYXNfdWludDMylEsBjAh1aW50ZWdlcpRKiH8deHVidWIu",
+        "n": "4",
+        "start": "0",
+        "_shape": [],
+        "dtype": "int64",
+        "_np_random": "Generator(PCG64)"
+    },
+    "n_envs": 1,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "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 sha256:9abc378f787a2758cb67761654e5cef6333ec995cbb6987a3bfb5bdc57e986ce
-size 1120
+oid sha256:476845959fecdf437367bed9cd670a5eb023e895a7c951871c48d58a608a2d05
+size 45216

dqn-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59c157a8c160d36c53022ecf24dc98708d274ea118083017b87978a9037c472
+oid sha256:e30b4443e37e89a959f479f32a738958f0157f2bce742e8650a1e4273a076f8a
 size 44338

dqn-LunarLander-v2/system_info.txt

@@ -1,9 +1,9 @@
-- 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
+- OS: Linux-6.2.0-1019-azure-x86_64-with-glibc2.36 # 19~22.04.1-Ubuntu SMP Wed Jan 10 22:57:03 UTC 2024
+- Python: 3.9.18
+- Stable-Baselines3: 2.1.0
+- PyTorch: 2.2.1+cpu
 - GPU Enabled: False
-- Numpy: 1.25.2
-- Cloudpickle: 2.2.1
+- Numpy: 1.26.4
+- Cloudpickle: 3.0.0
 - Gymnasium: 0.29.1
-- OpenAI Gym: 0.25.2
+- OpenAI Gym: 0.26.2

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a4df5a4d337b605583be1c4f5768ded9035585e1e14e5981d4fbcf255bf15b
-size 142014
+oid sha256:79b33a95867ba6a27dd005c3dececd1e3d953bdff47135c5fc5eed2817a4e204
+size 184963

results.json

@@ -1 +1 @@
-{"mean_reward": -249.17178186802192, "std_reward": 111.4377198808497, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T11:18:16.926725"}
+{"mean_reward": 41.67939652462665, "std_reward": 30.805182119145357, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-04T20:53:21.302318"}