Added replay video

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.16 +/- 0.10
+      value: -0.22 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e334faec9465ae896d58da5ba8d0bd18f41487829b8bc495e3c525832e1732a1
+oid sha256:8ffbea4912c59fefc0b7518fd6b0d54a4e67dd0a14e306af591d2a85b6296201
 size 106910

a2c-PandaReachDense-v3/data

@@ -4,9 +4,9 @@
         ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7be097b14a60>",
+        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7fcd3ceb9a20>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7be097b11540>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fcd3ceab1c0>"
     },
     "verbose": 1,
     "policy_kwargs": {

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7be097b14a60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7be097b11540>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1706374474717626270, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 2.1931033e-01 -7.9367298e-04  4.1859138e-01]\n [ 9.8986846e-01  4.3102834e-01  2.4692293e-01]\n [ 1.1601163e+00 -1.2255641e+00  7.0948344e-01]\n [-6.0419261e-01 -4.4164562e-01  3.2653636e-01]]", "desired_goal": "[[ 1.654419    0.8676513   1.5127661 ]\n [ 1.2481619   0.5433903  -0.35206142]\n [ 1.1230508  -1.658741    0.3914383 ]\n [ 0.1184776  -0.94439006  0.59815234]]", "observation": "[[ 2.1931033e-01 -7.9367298e-04  4.1859138e-01  4.8570773e-01\n   7.1406219e-04  3.8311595e-01]\n [ 9.8986846e-01  4.3102834e-01  2.4692293e-01  1.6317109e+00\n   1.6395770e+00 -1.1582586e+00]\n [ 1.1601163e+00 -1.2255641e+00  7.0948344e-01  5.3205365e-01\n  -9.0510345e-01 -3.8845515e-01]\n [-6.0419261e-01 -4.4164562e-01  3.2653636e-01 -8.5608190e-01\n  -1.6393442e+00  8.9008224e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[-0.06752931 -0.04415835  0.14047536]\n [ 0.00033373 -0.02854376  0.15234451]\n [-0.09341153 -0.08522998  0.16538036]\n [ 0.11619613  0.08580971  0.13963129]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 0, "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": 50000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.133+-x86_64-with-glibc2.35 # 1 SMP Tue Dec 19 13:14:11 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.0", "GPU Enabled": "True", "Numpy": "1.24.3", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.0", "OpenAI Gym": "0.26.2"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    MultiInputActorClass 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 (Tuple)\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: Uses the CombinedExtractor\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 MultiInputActorCriticPolicy.__init__ at 0x7fcd3ceb9a20>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fcd3ceab1c0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=", "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1706374474717626270, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 2.1931033e-01 -7.9367298e-04  4.1859138e-01]\n [ 9.8986846e-01  4.3102834e-01  2.4692293e-01]\n [ 1.1601163e+00 -1.2255641e+00  7.0948344e-01]\n [-6.0419261e-01 -4.4164562e-01  3.2653636e-01]]", "desired_goal": "[[ 1.654419    0.8676513   1.5127661 ]\n [ 1.2481619   0.5433903  -0.35206142]\n [ 1.1230508  -1.658741    0.3914383 ]\n [ 0.1184776  -0.94439006  0.59815234]]", "observation": "[[ 2.1931033e-01 -7.9367298e-04  4.1859138e-01  4.8570773e-01\n   7.1406219e-04  3.8311595e-01]\n [ 9.8986846e-01  4.3102834e-01  2.4692293e-01  1.6317109e+00\n   1.6395770e+00 -1.1582586e+00]\n [ 1.1601163e+00 -1.2255641e+00  7.0948344e-01  5.3205365e-01\n  -9.0510345e-01 -3.8845515e-01]\n [-6.0419261e-01 -4.4164562e-01  3.2653636e-01 -8.5608190e-01\n  -1.6393442e+00  8.9008224e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[-0.06752931 -0.04415835  0.14047536]\n [ 0.00033373 -0.02854376  0.15234451]\n [-0.09341153 -0.08522998  0.16538036]\n [ 0.11619613  0.08580971  0.13963129]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]\n [ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "_stats_window_size": 100, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHv9BxCIDYAbSMAWyUSwOMAXSUR0CnCW/ZVXFMdX2UKGgGR7+9ntfG+9J0aAdLAmgIR0CnCiaqsEJTdX2UKGgGR7+9ZOi35N48aAdLAmgIR0CnCXpOerdWdX2UKGgGR7/K3/giu+yraAdLA2gIR0CnCSMvRJEqdX2UKGgGR7/U9CNS619faAdLA2gIR0CnCjjX4CZGdX2UKGgGR7/c8Aq/dqL1aAdLBGgIR0CnCeUFbFCLdX2UKGgGR7/af16E8JUpaAdLBGgIR0CnCZCB5HEudX2UKGgGR7/T7lJYkmhNaAdLBGgIR0CnCTlSS/0vdX2UKGgGR7/Q62v0RODbaAdLA2gIR0CnCkdn003wdX2UKGgGR7/PtlZowmE5aAdLA2gIR0CnCfOm78NydX2UKGgGR7/Fq33Hq/ucaAdLA2gIR0CnCUrYwqRVdX2UKGgGR7/K580DU3GXaAdLA2gIR0CnCgTMqz7edX2UKGgGR7/dWWQfZElWaAdLBGgIR0CnCadzfaYedX2UKGgGR7/B13dKujh2aAdLAmgIR0CnCVT/p+tsdX2UKGgGR7/WkVvddmg8aAdLBWgIR0CnCmMiKR+0dX2UKGgGR7/NVsk6cRUWaAdLA2gIR0CnCbbYsd1ddX2UKGgGR7+3B7/n4fwJaAdLAmgIR0CnCV+XZ5AydX2UKGgGR7/MOXmeUY8/aAdLA2gIR0CnCnUxdpqRdX2UKGgGR7/XRLbpNbkfaAdLBWgIR0CnCiGATZg5dX2UKGgGR7/RsguAZsKtaAdLA2gIR0CnCcikoF3ZdX2UKGgGR7/OHfuTibUgaAdLA2gIR0CnCXGEPDpDdX2UKGgGR7/PpItlI3BIaAdLA2gIR0CnCoPikwevdX2UKGgGR7/QTKDCgsbvaAdLA2gIR0CnCi/9gnc+dX2UKGgGR7/CjAzpHI6saAdLAmgIR0CnCdK2SdOJdX2UKGgGR7/BzkIX0oSdaAdLAmgIR0CnCjzmOlwcdX2UKGgGR7/hde6Zpi7TaAdLBGgIR0CnCYhE0BOpdX2UKGgGR7/K2H+IdlunaAdLA2gIR0CnCpZtvXK9dX2UKGgGR7/UXuE25xzaaAdLA2gIR0CnCks36yjYdX2UKGgGR7/SS5y2hIvraAdLA2gIR0CnCqcjqv/zdX2UKGgGR7/e00WM0gr6aAdLBmgIR0CnCfYMWoFWdX2UKGgGR7/XvNu+AVfvaAdLBGgIR0CnCZ7MX7+DdX2UKGgGR7/TeCkGiYb9aAdLA2gIR0CnCl0cGTs6dX2UKGgGR7+6UFB6a9bpaAdLAmgIR0CnCf/R/mT1dX2UKGgGR7/OflIVdonKaAdLA2gIR0CnCrZ9NN8FdX2UKGgGR7/PiWE9Mbm2aAdLA2gIR0CnCa21twaSdX2UKGgGR7/CyJKraM72aAdLAmgIR0CnCmdvsJIEdX2UKGgGR7/MFqzqrzXjaAdLA2gIR0CnChGATZg5dX2UKGgGR7+951Ng0CRwaAdLAmgIR0CnCnQBo24vdX2UKGgGR7/S7YChew9raAdLA2gIR0CnCb+5WilBdX2UKGgGR7/WjUNKAavSaAdLBGgIR0CnCs5NoJzDdX2UKGgGR7+6qwQlKK51aAdLAmgIR0CnChzs6aLGdX2UKGgGR7+GoFV1fVqfaAdLAWgIR0CnCtNZV4ordX2UKGgGR7/MGBWgezUraAdLA2gIR0CnCc7dznzQdX2UKGgGR7/av/R3NcGDaAdLBGgIR0CnCovAfuCxdX2UKGgGR7/QYjjaPCEYaAdLA2gIR0CnCi5gG8mKdX2UKGgGR7/T2HtWuHN5aAdLBGgIR0CnCulK02LpdX2UKGgGR7/O5wwTM7lraAdLA2gIR0CnCpnlfZ27dX2UKGgGR7/SGvfTCtRvaAdLA2gIR0CnCjyZSeiBdX2UKGgGR7+70qYqoZQ6aAdLAmgIR0CnCvMoUi6hdX2UKGgGR7+dYwIt16mgaAdLAWgIR0CnCkHQY1pCdX2UKGgGR7/gL8iwB5ooaAdLBWgIR0CnCeqiXY16dX2UKGgGR7+ajzqbBoEkaAdLAWgIR0CnCvvBzmwJdX2UKGgGR7/UUJv5xiobaAdLA2gIR0CnCqyU9pyqdX2UKGgGR7/GS9M9KVY7aAdLAmgIR0CnCwXBpHqedX2UKGgGR7/I+PBBRhttaAdLA2gIR0CnClRkmQbNdX2UKGgGR7/TTNdJJ5E/aAdLA2gIR0CnCf0th/iHdX2UKGgGR7/emTC+De0paAdLBGgIR0CnCsPzFuNxdX2UKGgGR7/S+98JD3M7aAdLA2gIR0CnCma4lQdkdX2UKGgGR7/SDXvphWo4aAdLBGgIR0CnCx2M85jpdX2UKGgGR7/Utix3V09yaAdLBGgIR0CnChThHbypdX2UKGgGR7/J/y5I6KceaAdLA2gIR0CnCtO6/ZdwdX2UKGgGR7/Kj9GZuyeJaAdLA2gIR0CnCnZ57gKndX2UKGgGR7/SA6dUbT+eaAdLA2gIR0CnCy1ENOM3dX2UKGgGR7/X3wkPczqKaAdLBGgIR0CnCixLTQVsdX2UKGgGR7+5TLns9jgAaAdLAmgIR0CnCzo7FKkEdX2UKGgGR7/QP9kz41xbaAdLA2gIR0CnCuZi/fwadX2UKGgGR7/Rw+t8uzyCaAdLA2gIR0CnCokM9bHIdX2UKGgGR7/BRKpT/ACXaAdLAmgIR0CnC0P6sQumdX2UKGgGR7/QZpSJj2BbaAdLA2gIR0CnCjtVrAP/dX2UKGgGR7/Nc2R7qptKaAdLA2gIR0CnCvU6HTJAdX2UKGgGR7/YArhBJI1+aAdLBGgIR0CnCp+nqFAWdX2UKGgGR7/PjGT9sJpnaAdLA2gIR0CnC1Y+Sr5qdX2UKGgGR7/RQ1rIo3JgaAdLA2gIR0CnCk2G7BfsdX2UKGgGR7/AxqO938oAaAdLAmgIR0CnCqoBJZntdX2UKGgGR7/VOEdvKlpHaAdLBGgIR0CnCwxrzoU0dX2UKGgGR7/LVurIYFaCaAdLA2gIR0CnC2Vs1sLwdX2UKGgGR7+i5wwTM7lraAdLAWgIR0CnCxHmJWNndX2UKGgGR7+1YLb5/LDAaAdLAmgIR0CnCrSaNMoMdX2UKGgGR7/SwKBun/DMaAdLA2gIR0CnCl2Awwj/dX2UKGgGR7/D4QjD8+A3aAdLAmgIR0CnC3LrgOz6dX2UKGgGR7+8urZJ04ipaAdLAmgIR0CnCsGtyPuHdX2UKGgGR7+/MQmNR3vAaAdLAmgIR0CnCmpjMFEBdX2UKGgGR7+TyjHn2ZiNaAdLAWgIR0CnC3hYNiH7dX2UKGgGR7/IS3b212JSaAdLA2gIR0CnCyR8MNMHdX2UKGgGR7/JyU9pyp71aAdLA2gIR0CnCzUzKs+3dX2UKGgGR7/OIvalDWsjaAdLBGgIR0CnCtgzHjp+dX2UKGgGR7/a4CIUJv5yaAdLBGgIR0CnCoDv3JxOdX2UKGgGR7/QTBInSfDlaAdLBGgIR0CnC47jkuHvdX2UKGgGR7+9TAFgUlAvaAdLAmgIR0CnCooxxkupdX2UKGgGR7/GF7laKUFCaAdLA2gIR0CnC5z/Q0GedX2UKGgGR7/YZL7Gecx1aAdLBGgIR0CnC0lGXokidX2UKGgGR7/Q9PUKArhBaAdLBGgIR0CnCuvrv9cbdX2UKGgGR7/Tl0HQhOgyaAdLA2gIR0CnCpwpF1B/dX2UKGgGR7/EWIoE0SAZaAdLAmgIR0CnC1YS6DoRdX2UKGgGR7/Q3o9s7+1jaAdLA2gIR0CnC68IJJGwdX2UKGgGR7+g8hcJMQEqaAdLAWgIR0CnC1t+CsfadX2UKGgGR7/NTz/ZM+NcaAdLA2gIR0CnCv4rz5GjdX2UKGgGR7+h15jYqXnhaAdLAWgIR0CnC2BnJ1aGdX2UKGgGR7/Tt9hJAdGRaAdLA2gIR0CnCquObRWtdX2UKGgGR7/D4EfT1CgLaAdLAmgIR0CnC7mAbyYpdWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 50000, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True]", "bounded_above": "[ True  True  True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVqAIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS9vcHQvY29uZGEvbGliL3B5dGhvbjMuMTAvc2l0ZS1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvb3B0L2NvbmRhL2xpYi9weXRob24zLjEwL3NpdGUtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUaACMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RvAGjbi6x4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "system_info": {"OS": "Linux-5.15.133+-x86_64-with-glibc2.35 # 1 SMP Tue Dec 19 13:14:11 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.0", "GPU Enabled": "True", "Numpy": "1.24.3", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.0", "OpenAI Gym": "0.26.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -0.16260876022279264, "std_reward": 0.10148527446533663, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-27T17:52:45.018722"}
+{"mean_reward": -0.22012461386621, "std_reward": 0.12079029511570863, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-01-27T18:04:04.568256"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6672bc8dab0f2380b6d46c29e7ffeadaa17f93eb0b0125c37b481107fc81e66
-size 2636
+oid sha256:6ecb1e3f08898ae7397d9a066ab6621c1c44b339fadda59b210ca4e3274a229d
+size 2623