Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaPickAndPlace-v3
     metrics:
     - type: mean_reward
-      value: -45.00 +/- 15.00
+      value: -50.00 +/- 0.00
       name: mean_reward
       verified: false
 ---

a2c-PandaPickAndPlace-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05b1d3231c906a6d6c40407bc2d59e0683c237111ff3da62e3fd56e59f3d244
+oid sha256:6ece61a1ec61949b8402e9d07a9801d157ea7022a511bb9b85c58ec92aa90d9d
 size 124230

a2c-PandaPickAndPlace-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 0x7f779fc91b40>",
+        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7fc8e3881c60>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f779fc947c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7fc8e3885240>"
     },
     "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 0x7f779fc91b40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f779fc947c0>"}, "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": 1693664557733893158, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.7241946  -0.03735277  0.12579884]\n [ 0.2842969   0.8691161   0.12579884]\n [ 0.6716376  -0.2916548   0.12582076]\n [-0.91218954 -0.7967508   0.12580909]]", "desired_goal": "[[ 1.5558654  -1.6336695   0.29294994]\n [ 0.00228793 -0.3693578  -1.0942221 ]\n [-1.4248849  -0.33230814  1.7074101 ]\n [ 1.5350987   0.8041886   0.7766022 ]]", "observation": "[[ 0.12547344  0.47093973  0.01503237 -1.2328777   1.0202867  -0.86319613\n  -0.47267097  0.7241946  -0.03735277  0.12579884 -0.00388146  0.00842016\n  -0.01743987  0.04051799 -0.05056782  0.05981465  0.01654941 -0.01469605\n  -0.00792906]\n [-0.27240115 -0.17383087  0.7324084  -0.9627707   1.267847   -1.7471267\n   2.0749295   0.2842969   0.8691161   0.12579884 -0.00388146  0.00842016\n  -0.01743987  0.04051799 -0.05056782  0.05981465  0.01654941 -0.01469605\n  -0.00792906]\n [ 0.25625363 -0.26399174 -0.98547417  0.7688593  -0.027516    0.03344281\n  -0.47266728  0.6716376  -0.2916548   0.12582076 -0.00414457  0.00836195\n  -0.0167918   0.04069594 -0.05055008  0.05982695  0.01658771 -0.01474167\n  -0.00786056]\n [ 0.9534005   0.68718433 -0.94473106  0.02885787 -0.2709317  -0.65982324\n  -0.47267544 -0.91218954 -0.7967508   0.12580909 -0.00412408  0.00810266\n  -0.01744927  0.04069586 -0.05043422  0.05981465  0.01654941 -0.01469605\n  -0.00791598]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.10019325 -0.13425949  0.02      ]\n [ 0.12162775 -0.00856446  0.02      ]\n [ 0.14951038  0.06279156  0.02      ]\n [ 0.04129641  0.1319019   0.02      ]]", "desired_goal": "[[ 0.08593618 -0.08709429  0.02      ]\n [-0.06437515  0.00242832  0.03286916]\n [ 0.14542337  0.02917538  0.02      ]\n [ 0.07412328 -0.03205634  0.19163698]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00 -1.0019325e-01\n  -1.3425949e-01  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  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  0.0000000e+00  1.2162775e-01\n  -8.5644629e-03  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  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  0.0000000e+00  1.4951038e-01\n   6.2791556e-02  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  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  0.0000000e+00  4.1296408e-02\n   1.3190190e-01  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  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, (19,), 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  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWV8wIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMYC9ob21lL3lhb2h1YS9taW5pY29uZGEzL2VudnMvZHJsMi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4NDAgQBlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMYC9ob21lL3lhb2h1YS9taW5pY29uZGEzL2VudnMvZHJsMi9saWIvcHl0aG9uMy4xMC9zaXRlLXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/RvAGjbi6x4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "system_info": {"OS": "Linux-6.2.0-21-generic-x86_64-with-glibc2.37 # 21-Ubuntu SMP PREEMPT_DYNAMIC Fri Apr 14 12:34:02 UTC 2023", "Python": "3.10.10", "Stable-Baselines3": "2.1.0", "PyTorch": "2.1.0.dev20230609", "GPU Enabled": "True", "Numpy": "1.24.3", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1"}}
+{"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 0x7fc8e3881c60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fc8e3885240>"}, "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": 1693664557733893158, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.7241946  -0.03735277  0.12579884]\n [ 0.2842969   0.8691161   0.12579884]\n [ 0.6716376  -0.2916548   0.12582076]\n [-0.91218954 -0.7967508   0.12580909]]", "desired_goal": "[[ 1.5558654  -1.6336695   0.29294994]\n [ 0.00228793 -0.3693578  -1.0942221 ]\n [-1.4248849  -0.33230814  1.7074101 ]\n [ 1.5350987   0.8041886   0.7766022 ]]", "observation": "[[ 0.12547344  0.47093973  0.01503237 -1.2328777   1.0202867  -0.86319613\n  -0.47267097  0.7241946  -0.03735277  0.12579884 -0.00388146  0.00842016\n  -0.01743987  0.04051799 -0.05056782  0.05981465  0.01654941 -0.01469605\n  -0.00792906]\n [-0.27240115 -0.17383087  0.7324084  -0.9627707   1.267847   -1.7471267\n   2.0749295   0.2842969   0.8691161   0.12579884 -0.00388146  0.00842016\n  -0.01743987  0.04051799 -0.05056782  0.05981465  0.01654941 -0.01469605\n  -0.00792906]\n [ 0.25625363 -0.26399174 -0.98547417  0.7688593  -0.027516    0.03344281\n  -0.47266728  0.6716376  -0.2916548   0.12582076 -0.00414457  0.00836195\n  -0.0167918   0.04069594 -0.05055008  0.05982695  0.01658771 -0.01474167\n  -0.00786056]\n [ 0.9534005   0.68718433 -0.94473106  0.02885787 -0.2709317  -0.65982324\n  -0.47267544 -0.91218954 -0.7967508   0.12580909 -0.00412408  0.00810266\n  -0.01744927  0.04069586 -0.05043422  0.05981465  0.01654941 -0.01469605\n  -0.00791598]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.10019325 -0.13425949  0.02      ]\n [ 0.12162775 -0.00856446  0.02      ]\n [ 0.14951038  0.06279156  0.02      ]\n [ 0.04129641  0.1319019   0.02      ]]", "desired_goal": "[[ 0.08593618 -0.08709429  0.02      ]\n [-0.06437515  0.00242832  0.03286916]\n [ 0.14542337  0.02917538  0.02      ]\n [ 0.07412328 -0.03205634  0.19163698]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00  0.0000000e+00 -1.0019325e-01\n  -1.3425949e-01  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  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  0.0000000e+00  1.2162775e-01\n  -8.5644629e-03  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  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  0.0000000e+00  1.4951038e-01\n   6.2791556e-02  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  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  0.0000000e+00  4.1296408e-02\n   1.3190190e-01  2.0000000e-02  0.0000000e+00 -0.0000000e+00\n   0.0000000e+00  0.0000000e+00  0.0000000e+00  0.0000000e+00\n   0.0000000e+00  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:": "gAWVMgQAAAAAAACMFWd5bW5hc2l1bS5zcGFjZXMuZGljdJSMBERpY3SUk5QpgZR9lCiMBnNwYWNlc5SMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwUZ3ltbmFzaXVtLnNwYWNlcy5ib3iUjANCb3iUk5QpgZR9lCiMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowNYm91bmRlZF9iZWxvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYDAAAAAAAAAAEBAZRoE4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksDhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoHCiWAwAAAAAAAAABAQGUaCBLA4WUaCR0lFKUjAZfc2hhcGWUSwOFlIwDbG93lGgcKJYMAAAAAAAAAAAAIMEAACDBAAAgwZRoFksDhZRoJHSUUpSMBGhpZ2iUaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlIwIbG93X3JlcHKUjAUtMTAuMJSMCWhpZ2hfcmVwcpSMBDEwLjCUjApfbnBfcmFuZG9tlE51YowMZGVzaXJlZF9nb2FslGgNKYGUfZQoaBBoFmgZaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgnaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgsSwOFlGguaBwolgwAAAAAAAAAAAAgwQAAIMEAACDBlGgWSwOFlGgkdJRSlGgzaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlGg4jAUtMTAuMJRoOowEMTAuMJRoPE51YowLb2JzZXJ2YXRpb26UaA0pgZR9lChoEGgWaBloHCiWEwAAAAAAAAABAQEBAQEBAQEBAQEBAQEBAQEBlGggSxOFlGgkdJRSlGgnaBwolhMAAAAAAAAAAQEBAQEBAQEBAQEBAQEBAQEBAZRoIEsThZRoJHSUUpRoLEsThZRoLmgcKJZMAAAAAAAAAAAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMEAACDBAAAgwQAAIMGUaBZLE4WUaCR0lFKUaDNoHCiWTAAAAAAAAAAAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBAAAgQQAAIEEAACBBlGgWSxOFlGgkdJRSlGg4jAUtMTAuMJRoOowEMTAuMJRoPE51YnVoLE5oEE5oPE51Yi4=", "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, (19,), 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  True]", "bounded_above": "[ True  True  True  True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 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-6.2.0-21-generic-x86_64-with-glibc2.37 # 21-Ubuntu SMP PREEMPT_DYNAMIC Fri Apr 14 12:34:02 UTC 2023", "Python": "3.10.10", "Stable-Baselines3": "2.1.0", "PyTorch": "2.1.0.dev20230609", "GPU Enabled": "True", "Numpy": "1.24.3", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -45.0, "std_reward": 15.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-02T22:52:04.061054"}
+{"mean_reward": -50.0, "std_reward": 0.0, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-02T22:57:37.547129"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4239f77e935897f7ecc63860c68aa4dc337e76053c34b59e8a4cc86ebc4ae50
+oid sha256:0317fc27cd6e1850b637133a9c5bd95f7f112467b2fc1bd48102d9fbd90f52ad
 size 3013