model

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pusher-v5
     metrics:
     - type: mean_reward
-      value: -29.51 +/- 5.83
+      value: -29.87 +/- 5.96
       name: mean_reward
       verified: false
 ---

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=", "__module__": "stable_baselines3.sac.policies", "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}", "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function SACPolicy.__init__ at 0x7fcff7808e00>", "_build": "<function SACPolicy._build at 0x7fcff78093a0>", "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fcff7809440>", "reset_noise": "<function SACPolicy.reset_noise at 0x7fcff78094e0>", "make_actor": "<function SACPolicy.make_actor at 0x7fcff7809580>", "make_critic": "<function SACPolicy.make_critic at 0x7fcff7809620>", "forward": "<function SACPolicy.forward at 0x7fcff78096c0>", "_predict": "<function SACPolicy._predict at 0x7fcff7809760>", "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fcff7809800>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fcff7810f00>"}, "verbose": 0, "policy_kwargs": {"use_sde": false}, "num_timesteps": 865000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": 0, "action_noise": null, "start_time": 1735587324143850684, "learning_rate": 0.0003, "tensorboard_log": "runs/0", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYFAAAAAAAAAAEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksFhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 8645, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.13500500000000004, "_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": 170999, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 10000, "tau": 0.005, "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 0x7fd0026e0d60>", "add": "<function ReplayBuffer.add at 0x7fd0026e0ea0>", "sample": "<function ReplayBuffer.sample at 0x7fd0026e0f40>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7fd0026e0fe0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fd0026e1080>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fd0026d7680>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -7.0, "ent_coef": "auto", "target_update_interval": 1, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float64", "_shape": [23], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [7], "low": "[-2. -2. -2. -2. -2. -2. -2.]", "bounded_below": "[ True  True  True  True  True  True  True]", "high": "[2. 2. 2. 2. 2. 2. 2.]", "bounded_above": "[ True  True  True  True  True  True  True]", "low_repr": "-2.0", "high_repr": "2.0", "_np_random": "Generator(PCG64)"}, "n_envs": 5, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.125-1-MANJARO-x86_64-with-glibc2.40 # 1 SMP PREEMPT_DYNAMIC Fri Jan 17 15:04:03 UTC 2025", "Python": "3.12.8", "Stable-Baselines3": "2.4.1", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "1.0.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVMAAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMCVNBQ1BvbGljeZSTlC4=", "__module__": "stable_baselines3.sac.policies", "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}", "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ", "__init__": "<function SACPolicy.__init__ at 0x7fe777154e00>", "_build": "<function SACPolicy._build at 0x7fe7771553a0>", "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fe777155440>", "reset_noise": "<function SACPolicy.reset_noise at 0x7fe7771554e0>", "make_actor": "<function SACPolicy.make_actor at 0x7fe777155580>", "make_critic": "<function SACPolicy.make_critic at 0x7fe777155620>", "forward": "<function SACPolicy.forward at 0x7fe7771556c0>", "_predict": "<function SACPolicy._predict at 0x7fe777155760>", "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fe777155800>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fe77715cb80>"}, "verbose": 0, "policy_kwargs": {"use_sde": false}, "num_timesteps": 865000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": 0, "action_noise": null, "start_time": 1735587324143850684, "learning_rate": 0.0003, "tensorboard_log": "runs/0", "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYFAAAAAAAAAAEBAQEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksFhZSMAUOUdJRSlC4="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 8645, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.13500500000000004, "_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": 170999, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 10000, "tau": 0.005, "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 0x7fe781f50d60>", "add": "<function ReplayBuffer.add at 0x7fe781f50ea0>", "sample": "<function ReplayBuffer.sample at 0x7fe781f50f40>", "_get_samples": "<function ReplayBuffer._get_samples at 0x7fe781f50fe0>", "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fe781f51080>)>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fe781f4a540>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -7.0, "ent_coef": "auto", "target_update_interval": 1, "observation_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float64", "_shape": [23], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [7], "low": "[-2. -2. -2. -2. -2. -2. -2.]", "bounded_below": "[ True  True  True  True  True  True  True]", "high": "[2. 2. 2. 2. 2. 2. 2.]", "bounded_above": "[ True  True  True  True  True  True  True]", "low_repr": "-2.0", "high_repr": "2.0", "_np_random": "Generator(PCG64)"}, "n_envs": 5, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVRgQAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLBUsTQyaVAZcAdAEAAAAAAAAAAAIAiQF8AKsBAAAAAAAAqwEAAAAAAABTAJROhZSMBWZsb2F0lIWUjBJwcm9ncmVzc19yZW1haW5pbmeUhZSMaC9ob21lL21hc3Rlci1hbmRyZWFzL2dlbl9kYXRhc2V0L3Rlc3RfZW52L2xpYi9weXRob24zLjEyL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwIPGxhbWJkYT6UjCFnZXRfc2NoZWR1bGVfZm4uPGxvY2Fscz4uPGxhbWJkYT6US2FDEPiAAKRlqU7QO03TLE7UJk+UQwCUjA52YWx1ZV9zY2hlZHVsZZSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjGgvaG9tZS9tYXN0ZXItYW5kcmVhcy9nZW5fZGF0YXNldC90ZXN0X2Vudi9saWIvcHl0aG9uMy4xMi9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoI32UfZQoaBqMCDxsYW1iZGE+lIwMX19xdWFsbmFtZV9flIwhZ2V0X3NjaGVkdWxlX2ZuLjxsb2NhbHM+LjxsYW1iZGE+lIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoG4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlGgCKGgHKEsBSwBLAEsBSwFLE0MIlQGXAIkBUwCUaAkpjAFflIWUaA6MBGZ1bmOUjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlEuFQwj4gADYDxKICpRoEowDdmFslIWUKXSUUpRoF05OaB8pUpSFlHSUUpRoJWhBfZR9lChoGowEZnVuY5RoKYwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5RoK32UaC1OaC5OaC9oG2gwTmgxaDNHPzOpKjBVMmGFlFKUhZSMF19jbG91ZHBpY2tsZV9zdWJtb2R1bGVzlF2UjAtfX2dsb2JhbHNfX5R9lHWGlIZSMIWUUpSFlGhKXZRoTH2UdYaUhlIwLg=="}, "batch_norm_stats": [], "batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.125-1-MANJARO-x86_64-with-glibc2.40 # 1 SMP PREEMPT_DYNAMIC Fri Jan 17 15:04:03 UTC 2025", "Python": "3.12.8", "Stable-Baselines3": "2.4.1", "PyTorch": "2.5.1+cu124", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "1.0.0"}}

pusher-v5-SAC-medium.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d32e260714ef1f49ed26ed643b186cffe320a3799806830b3dfafc772be03761
+oid sha256:6ad4f083db0713cb5c6ec649cbcff50c5205e25c78756aed89f9921d75b1d2b8
 size 3325310

pusher-v5-SAC-medium/data

@@ -5,17 +5,17 @@
         "__module__": "stable_baselines3.sac.policies",
         "__annotations__": "{'actor': <class 'stable_baselines3.sac.policies.Actor'>, 'critic': <class 'stable_baselines3.common.policies.ContinuousCritic'>, 'critic_target': <class 'stable_baselines3.common.policies.ContinuousCritic'>}",
         "__doc__": "\n    Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\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    :param n_critics: Number of critic networks to create.\n    :param share_features_extractor: Whether to share or not the features extractor\n        between the actor and the critic (this saves computation time)\n    ",
-        "__init__": "<function SACPolicy.__init__ at 0x7fcff7808e00>",
-        "_build": "<function SACPolicy._build at 0x7fcff78093a0>",
-        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fcff7809440>",
-        "reset_noise": "<function SACPolicy.reset_noise at 0x7fcff78094e0>",
-        "make_actor": "<function SACPolicy.make_actor at 0x7fcff7809580>",
-        "make_critic": "<function SACPolicy.make_critic at 0x7fcff7809620>",
-        "forward": "<function SACPolicy.forward at 0x7fcff78096c0>",
-        "_predict": "<function SACPolicy._predict at 0x7fcff7809760>",
-        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fcff7809800>",
+        "__init__": "<function SACPolicy.__init__ at 0x7fe777154e00>",
+        "_build": "<function SACPolicy._build at 0x7fe7771553a0>",
+        "_get_constructor_parameters": "<function SACPolicy._get_constructor_parameters at 0x7fe777155440>",
+        "reset_noise": "<function SACPolicy.reset_noise at 0x7fe7771554e0>",
+        "make_actor": "<function SACPolicy.make_actor at 0x7fe777155580>",
+        "make_critic": "<function SACPolicy.make_critic at 0x7fe777155620>",
+        "forward": "<function SACPolicy.forward at 0x7fe7771556c0>",
+        "_predict": "<function SACPolicy._predict at 0x7fe777155760>",
+        "set_training_mode": "<function SACPolicy.set_training_mode at 0x7fe777155800>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fcff7810f00>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fe77715cb80>"
     },
     "verbose": 0,
     "policy_kwargs": {
@@ -68,13 +68,13 @@
         "__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 0x7fd0026e0d60>",
-        "add": "<function ReplayBuffer.add at 0x7fd0026e0ea0>",
-        "sample": "<function ReplayBuffer.sample at 0x7fd0026e0f40>",
-        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fd0026e0fe0>",
-        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fd0026e1080>)>",
+        "__init__": "<function ReplayBuffer.__init__ at 0x7fe781f50d60>",
+        "add": "<function ReplayBuffer.add at 0x7fe781f50ea0>",
+        "sample": "<function ReplayBuffer.sample at 0x7fe781f50f40>",
+        "_get_samples": "<function ReplayBuffer._get_samples at 0x7fe781f50fe0>",
+        "_maybe_cast_dtype": "<staticmethod(<function ReplayBuffer._maybe_cast_dtype at 0x7fe781f51080>)>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7fd0026d7680>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fe781f4a540>"
     },
     "replay_buffer_kwargs": {},
     "train_freq": {

results.json

@@ -1 +1 @@
-{"mean_reward": -29.512588586, "std_reward": 5.834652673886785, "is_deterministic": true, "n_eval_episodes": 1000, "eval_datetime": "2025-01-26T12:50:18.365308"}
+{"mean_reward": -29.865848729000003, "std_reward": 5.963645844602234, "is_deterministic": true, "n_eval_episodes": 1000, "eval_datetime": "2025-01-26T16:27:21.534486"}