Train with 100,000 steps

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -176.71 +/- 42.84
+      value: -102.68 +/- 29.24
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ActorCriticPolicy.__init__ at 0x7fae14e423b0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fae14e42440>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fae14e424d0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fae14e42560>", "_build": "<function ActorCriticPolicy._build at 0x7fae14e425f0>", "forward": "<function ActorCriticPolicy.forward at 0x7fae14e42680>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fae14e42710>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fae14e427a0>", "_predict": "<function ActorCriticPolicy._predict at 0x7fae14e42830>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fae14e428c0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fae14e42950>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fae14e429e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fae14de7080>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 131072, "_total_timesteps": 100000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711290930694592224, "learning_rate": 0.0003, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAJrzNTzLALc/8LoFPhcv8zySR2g8xu2mPQAAAAAAAAAAs2FBvQ8CIz+eVPY99ph2v6xJ474meke+AAAAAAAAAABYst2+drRYPyb9pL48mge/qHPWvgOwbL4AAAAAAAAAAA0ogb2xc8A9q6OnPpU1k78TM5i9XaBYPgAAAAAAAAAAADAYvJrVqj/91sK9p37FvlCR77zTZA6+AAAAAAAAAADN9lU86bG0P1u7CT7Fdqe9URuDvK8uoLwAAAAAAAAAAOa3ob0BQ0M/pGNCvlToSb82r7S99RUJvgAAAAAAAAAAhbC7voGzCT9uQcC+U5p4v1utOb500jW9AAAAAAAAAAAz0+88UtO0P+LKYj7UcJM8KB7POxXZKj0AAAAAAAAAAGb6P7xnDpU/imeVvI1IIr/gXDc9JnrgvQAAAAAAAAAAE0MePi4DuT9CLQA/StflvT5fxj0CdQM+AAAAAAAAAADmEFy9ZCe7PzpUer1EzoO+h1oHvmIDA74AAAAAAAAAAM1ExTv3VpQ/HkcYPtszB7+kvqy+uqmQvgAAAAAAAAAAGqeHvY/MhD+CFhi+sEofv9CMQr0ncx2+AAAAAAAAAAASZ6y+3VWpPyRSvb68lOu+qGwcv4IO0r4AAAAAAAAAAE0jHz5elig/8giBPorVe79dMBc+zRk6PQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -0.3107200000000001, "_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": 40, "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": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         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": 16, "n_steps": 2048, "gamma": 0.99, "gae_lambda": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "batch_size": 64, "n_epochs": 10, "clip_range": {":type:": "<class 'function'>", ":serialized:": "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"}, "clip_range_vf": null, "normalize_advantage": true, "target_kl": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "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": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "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 0x7fae14e80af0>", "_build": "<function DQNPolicy._build at 0x7fae14e80b80>", "make_q_net": "<function DQNPolicy.make_q_net at 0x7fae14e80c10>", "forward": "<function DQNPolicy.forward at 0x7fae14e80ca0>", "_predict": "<function DQNPolicy._predict at 0x7fae14e80d30>", "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fae14e80dc0>", "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fae14e80e50>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fae14e6adc0>"}, "verbose": 1, "policy_kwargs": {}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711291427254821940, "learning_rate": 0.0001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdQIAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYAAgAAAAAAAAAgnTujoGU/hE2vvPn9N7w6mGC9SnqfPQAAAAAAAAAAljGiPmvEoz/uoPs963WHvPv3sj41EwC+AAAAAAAAAACT3AI+bEK2P0VGlDrykuU6qmraPeEAub0AAAAAAAAAAJoNBz3x76w/4AvwO8pEAL2Tijw9Ug4TPQAAAAAAAAAA05s0PlzCjj+1cDU8BsIovMLbyTzuBcE9AAAAAAAAAADmNGk9A7yxP9CuaL0p4FG8nf1AvYJ2Wr0AAAAAAAAAAAMKlD66dKQ/6CMKPQOZnjxQa/I9dqyAuwAAAAAAAAAA5tiGPURClD+Wc3k8jm7RvJI0Bj2Aw2s8AAAAAAAAAACGPgm+jtudP32jpzzPBGw8wM0gPbNQjjsAAAAAAAAAAA11u70TsXI/wKVWPNpd6byRzw88ywH7PAAAAAAAAAAA2qJ3PiKPqD+ZnTQ9eSsCvQIqxD3uRl08AAAAAAAAAADmZnW9OEG/P2qQ4r6sBSY+VM5FvV5Clb4AAAAAAAAAAMD5qT2bg5Q/WLxovEklPbsrggK99WPDPAAAAAAAAAAARgTVPtCIiT83Cbg+qoyKPWlt2j6Wajs+AAAAAAAAAACa8Y+9RZepP2zdJzwVuR28y4H8PGNiqTwAAAAAAAAAADMdpD59A40/kOw/O9GA47wBE7Q9FqBqvQAAAAAAAAAAlIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksQSwiGlIwBQ5R0lFKULg=="}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 1896, "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": 14844, "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": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high": "[90.        90.         5.         5.         3.1415927  5.\n  1.         1.       ]", "low_repr": "[-90.        -90.         -5.         -5.         -3.1415927  -5.\n  -0.         -0.       ]", "high_repr": "[90.        90.         5.         5.         3.1415927  5.\n  1.         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": 16, "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 0x7fae14e58f70>", "add": "<function ReplayBuffer.add at 0x7fae14e59000>", "sample": "<function ReplayBuffer.sample at 0x7fae14e59090>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7fae14e59120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fae14e55e80>"}, "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": 625, "_n_calls": 62500, "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-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": "2.0.0a5", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb09185305d212f045595a6dfde2e208449a7ccae0d3c31a1729268f2f4f9cd4
-size 147950
+oid sha256:eaba4af5f91285d372d4f4e04931bde86791223f759b3c49748beca8b5864da7
+size 108028

ppo-LunarLander-v2/data

@@ -1,57 +1,56 @@
 {
     "policy_class": {
         ":type:": "<class 'abc.ABCMeta'>",
-        ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
-        "__module__": "stable_baselines3.common.policies",
-        "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\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 ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\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 share_features_extractor: If True, the features extractor is shared between the policy and value networks.\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 ActorCriticPolicy.__init__ at 0x7fae14e423b0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7fae14e42440>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7fae14e424d0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7fae14e42560>",
-        "_build": "<function ActorCriticPolicy._build at 0x7fae14e425f0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7fae14e42680>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7fae14e42710>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7fae14e427a0>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7fae14e42830>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7fae14e428c0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7fae14e42950>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7fae14e429e0>",
+        ":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 0x7fae14e80af0>",
+        "_build": "<function DQNPolicy._build at 0x7fae14e80b80>",
+        "make_q_net": "<function DQNPolicy.make_q_net at 0x7fae14e80c10>",
+        "forward": "<function DQNPolicy.forward at 0x7fae14e80ca0>",
+        "_predict": "<function DQNPolicy._predict at 0x7fae14e80d30>",
+        "_get_constructor_parameters": "<function DQNPolicy._get_constructor_parameters at 0x7fae14e80dc0>",
+        "set_training_mode": "<function DQNPolicy.set_training_mode at 0x7fae14e80e50>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fae14de7080>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fae14e6adc0>"
     },
     "verbose": 1,
     "policy_kwargs": {},
-    "num_timesteps": 131072,
-    "_total_timesteps": 100000,
+    "num_timesteps": 1000000,
+    "_total_timesteps": 1000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1711290930694592224,
-    "learning_rate": 0.0003,
+    "start_time": 1711291427254821940,
+    "learning_rate": 0.0001,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVgwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYQAAAAAAAAAAEBAQEBAQEBAQEBAQEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSxCFlIwBQ5R0lFKULg=="
     },
-    "_last_original_obs": null,
-    "_episode_num": 0,
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_episode_num": 1896,
     "use_sde": false,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": -0.3107200000000001,
+    "_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'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 40,
+    "_n_updates": 14844,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.box.Box'>",
         ":serialized:": "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",
@@ -69,31 +68,54 @@
     },
     "action_space": {
         ":type:": "<class 'gymnasium.spaces.discrete.Discrete'>",
-        ":serialized:": "gAWV2wAAAAAAAACMGWd5bW5hc2l1bS5zcGFjZXMuZGlzY3JldGWUjAhEaXNjcmV0ZZSTlCmBlH2UKIwBbpSMFW51bXB5LmNvcmUubXVsdGlhcnJheZSMBnNjYWxhcpSTlIwFbnVtcHmUjAVkdHlwZZSTlIwCaTiUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYkMIBAAAAAAAAACUhpRSlIwFc3RhcnSUaAhoDkMIAAAAAAAAAACUhpRSlIwGX3NoYXBllCmMBWR0eXBllGgOjApfbnBfcmFuZG9tlE51Yi4=",
+        ":serialized:": "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",
         "n": "4",
         "start": "0",
         "_shape": [],
         "dtype": "int64",
-        "_np_random": null
+        "_np_random": "Generator(PCG64)"
     },
     "n_envs": 16,
-    "n_steps": 2048,
+    "buffer_size": 1000000,
+    "batch_size": 32,
+    "learning_starts": 50000,
+    "tau": 1.0,
     "gamma": 0.99,
-    "gae_lambda": 0.95,
-    "ent_coef": 0.0,
-    "vf_coef": 0.5,
-    "max_grad_norm": 0.5,
-    "batch_size": 64,
-    "n_epochs": 10,
-    "clip_range": {
-        ":type:": "<class 'function'>",
-        ":serialized:": "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"
+    "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 0x7fae14e58f70>",
+        "add": "<function ReplayBuffer.add at 0x7fae14e59000>",
+        "sample": "<function ReplayBuffer.sample at 0x7fae14e59090>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fae14e59120>",
+        "__abstractmethods__": "frozenset()",
+        "_abc_impl": "<_abc._abc_data object at 0x7fae14e55e80>"
+    },
+    "replay_buffer_kwargs": {},
+    "train_freq": {
+        ":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
+        ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLBGgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
     },
-    "clip_range_vf": null,
-    "normalize_advantage": true,
-    "target_kl": null,
+    "use_sde_at_warmup": false,
+    "exploration_initial_eps": 1.0,
+    "exploration_final_eps": 0.05,
+    "exploration_fraction": 0.1,
+    "target_update_interval": 625,
+    "_n_calls": 62500,
+    "max_grad_norm": 10,
+    "exploration_rate": 0.05,
     "lr_schedule": {
         ":type:": "<class 'function'>",
-        ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuEQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz8zqSowVTJhhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"
+        ":serialized:": "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"
+    },
+    "batch_norm_stats": [],
+    "batch_norm_stats_target": [],
+    "exploration_schedule": {
+        ":type:": "<class 'function'>",
+        ":serialized:": "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"
     }
 }

ppo-LunarLander-v2/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba09ab0186cbb0dd8837452bc87233bdca3dde97582f674ae237ac57a884dae4
-size 88362
+oid sha256:37ca720cb526cbe1531087e03a6969000d0f5451e71b5b19c78d3aaafbfc7e46
+size 45344

ppo-LunarLander-v2/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abec52755bb9c7dea41a2a42cb4374007b0271c12109e43f40ad399b232bda61
-size 43762
+oid sha256:b771bd7f34f7502b7813b34dcb1456690b7ce9b43eebbc5bbab9401332cfe3c4
+size 44466

results.json

@@ -1 +1 @@
-{"mean_reward": -176.7072887, "std_reward": 42.843947502531044, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-24T14:39:17.886381"}
+{"mean_reward": -102.6786815, "std_reward": 29.244557068583752, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-24T15:10:08.602732"}