scratc train 20 mil

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -34.17 +/- 11.84
+      value: -0.20 +/- 0.09
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be35d8de3c1fd1a55ec023e2e823a948870614e2a57e9655404760c3953299af
-size 101343
+oid sha256:58a666d2ed8f832360bc80ecfa5bec60a0f792ae4f02780d68024f5897f9ca18
+size 106854

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 0x0000025519EBA520>",
+        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x000001AA22CC6520>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x0000025519EA7780>"
+        "_abc_impl": "<_abc._abc_data object at 0x000001AA22CC2B00>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -19,31 +19,31 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 6000000,
-    "_total_timesteps": 6000000,
+    "num_timesteps": 20000000,
+    "_total_timesteps": 20000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1693632942106619000,
+    "start_time": 1693894566703965600,
     "learning_rate": 0.0007,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAAN4b9Ptd6xL+go2a/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAw8Ksv3WgY79nybY/lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAAA3hv0+13rEv6CjZr9/4J0+p9M0PMNWkD2UaA5LAUsGhpRoEnSUUpR1Lg==",
-        "achieved_goal": "[[ 0.4951646 -1.5349988 -0.9009342]]",
-        "desired_goal": "[[-1.3496937  -0.88916713  1.4280213 ]]",
-        "observation": "[[ 0.4951646  -1.5349988  -0.9009342   0.3083534   0.01103679  0.07047798]]"
+        ":serialized:": "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",
+        "achieved_goal": "[[ 1.364975   -1.6208115   1.3819735 ]\n [ 0.3355674   0.00391466  0.4746808 ]\n [ 0.05760562  1.7130919   1.4988613 ]\n [ 0.3355674   0.00391466  0.4746808 ]]",
+        "desired_goal": "[[ 1.5217215  -0.87037563  0.9918443 ]\n [-0.5598176   0.27933985 -0.3726359 ]\n [ 0.07788423  1.5105311   1.6533182 ]\n [-0.31576985 -0.979538   -0.06553492]]",
+        "observation": "[[ 1.3649750e+00 -1.6208115e+00  1.3819735e+00  1.0178519e+00\n  -9.5592672e-01  1.0186501e+00]\n [ 3.3556741e-01  3.9146566e-03  4.7468081e-01  5.0580305e-01\n  -1.0569901e-03  3.9538592e-01]\n [ 5.7605624e-02  1.7130919e+00  1.4988613e+00  5.3816527e-01\n   1.0056447e+00  1.6789471e+00]\n [ 3.3556741e-01  3.9146566e-03  4.7468081e-01  5.0580305e-01\n  -1.0569901e-03  3.9538592e-01]]"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAA9kf4vR42Fz5Hnis+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==",
-        "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]",
-        "desired_goal": "[[-0.121231    0.14766738  0.16759597]]",
-        "observation": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01  0.0000000e+00\n  -0.0000000e+00  0.0000000e+00]]"
+        ":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": "[[ 0.00354649  0.13513911  0.04324788]\n [-0.07151636 -0.06045266  0.24426772]\n [-0.12430525 -0.07895685  0.24038234]\n [ 0.13291684  0.00339827  0.2928731 ]]",
+        "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,
@@ -52,13 +52,13 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 2514430,
+    "_n_updates": 1000000,
     "n_steps": 5,
     "gamma": 0.99,
     "gae_lambda": 1.0,
@@ -89,7 +89,7 @@
         "high_repr": "1.0",
         "_np_random": "Generator(PCG64)"
     },
-    "n_envs": 1,
+    "n_envs": 4,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"

a2c-PandaReachDense-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20eb105aa0e042c23a33da5964cdd9c16b6f42f5454249a1f79173ca62042560
+oid sha256:6a3516b8519533913006ee3d6ac855ed2bfc050c77175d02af189d682002ffd1
 size 44606

a2c-PandaReachDense-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d5b05c44982c1750e054142dce0a92c7b5ebf70f89f47674c355bbd2cd7aea9
+oid sha256:064895da50004c010ecd7f970fd61097380422941dfc9e36a9206734362386ee
 size 45886

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 0x0000025519EBA520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000025519EA7780>"}, "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": 6000000, "_total_timesteps": 6000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693632942106619000, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAAN4b9Ptd6xL+go2a/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAAw8Ksv3WgY79nybY/lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAAA3hv0+13rEv6CjZr9/4J0+p9M0PMNWkD2UaA5LAUsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[ 0.4951646 -1.5349988 -0.9009342]]", "desired_goal": "[[-1.3496937  -0.88916713  1.4280213 ]]", "observation": "[[ 0.4951646  -1.5349988  -0.9009342   0.3083534   0.01103679  0.07047798]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdAAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYBAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwGFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVKwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QolgwAAAAAAAAA6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksBSwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcolgwAAAAAAAAA9kf4vR42Fz5Hnis+lGgOSwFLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWGAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LAUsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[ 3.8439669e-02 -2.1944723e-12  1.9740014e-01]]", "desired_goal": "[[-0.121231    0.14766738  0.16759597]]", "observation": "[[ 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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 2514430, "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": "Generator(PCG64)"}, "n_envs": 1, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.11.0", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cpu", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "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 0x000001AA22CC6520>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x000001AA22CC2B00>"}, "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": 20000000, "_total_timesteps": 20000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1693894566703965600, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 1.364975   -1.6208115   1.3819735 ]\n [ 0.3355674   0.00391466  0.4746808 ]\n [ 0.05760562  1.7130919   1.4988613 ]\n [ 0.3355674   0.00391466  0.4746808 ]]", "desired_goal": "[[ 1.5217215  -0.87037563  0.9918443 ]\n [-0.5598176   0.27933985 -0.3726359 ]\n [ 0.07788423  1.5105311   1.6533182 ]\n [-0.31576985 -0.979538   -0.06553492]]", "observation": "[[ 1.3649750e+00 -1.6208115e+00  1.3819735e+00  1.0178519e+00\n  -9.5592672e-01  1.0186501e+00]\n [ 3.3556741e-01  3.9146566e-03  4.7468081e-01  5.0580305e-01\n  -1.0569901e-03  3.9538592e-01]\n [ 5.7605624e-02  1.7130919e+00  1.4988613e+00  5.3816527e-01\n   1.0056447e+00  1.6789471e+00]\n [ 3.3556741e-01  3.9146566e-03  4.7468081e-01  5.0580305e-01\n  -1.0569901e-03  3.9538592e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[ 0.00354649  0.13513911  0.04324788]\n [-0.07151636 -0.06045266  0.24426772]\n [-0.12430525 -0.07895685  0.24038234]\n [ 0.13291684  0.00339827  0.2928731 ]]", "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": 1000000, "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:": "gAWVsAMAAAAAAACMFWd5bW5hc2l1bS5zcGFjZXMuZGljdJSMBERpY3SUk5QpgZR9lCiMBnNwYWNlc5SMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwUZ3ltbmFzaXVtLnNwYWNlcy5ib3iUjANCb3iUk5QpgZR9lCiMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowNYm91bmRlZF9iZWxvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYDAAAAAAAAAAEBAZRoE4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksDhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoHCiWAwAAAAAAAAABAQGUaCBLA4WUaCR0lFKUjAZfc2hhcGWUSwOFlIwDbG93lGgcKJYMAAAAAAAAAAAAIMEAACDBAAAgwZRoFksDhZRoJHSUUpSMBGhpZ2iUaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlIwIbG93X3JlcHKUjAUtMTAuMJSMCWhpZ2hfcmVwcpSMBDEwLjCUjApfbnBfcmFuZG9tlE51YowMZGVzaXJlZF9nb2FslGgNKYGUfZQoaBBoFmgZaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgnaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgsSwOFlGguaBwolgwAAAAAAAAAAAAgwQAAIMEAACDBlGgWSwOFlGgkdJRSlGgzaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlGg4jAUtMTAuMJRoOowEMTAuMJRoPE51YowLb2JzZXJ2YXRpb26UaA0pgZR9lChoEGgWaBloHCiWBgAAAAAAAAABAQEBAQGUaCBLBoWUaCR0lFKUaCdoHCiWBgAAAAAAAAABAQEBAQGUaCBLBoWUaCR0lFKUaCxLBoWUaC5oHCiWGAAAAAAAAAAAACDBAAAgwQAAIMEAACDBAAAgwQAAIMGUaBZLBoWUaCR0lFKUaDNoHCiWGAAAAAAAAAAAACBBAAAgQQAAIEEAACBBAAAgQQAAIEGUaBZLBoWUaCR0lFKUaDiMBS0xMC4wlGg6jAQxMC4wlGg8TnVidWgsTmgQTmg8TnViLg==", "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": "Generator(PCG64)"}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVngIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwiVAZcAiQFTAJROhZQpjAFflIWUjF1jOlxVc2Vyc1xBZG1pblxhbmFjb25kYTNcZW52c1xodWdnaW5nZmFjZVxMaWJcc2l0ZS1wYWNrYWdlc1xzdGFibGVfYmFzZWxpbmVzM1xjb21tb25cdXRpbHMucHmUjARmdW5jlIwZY29uc3RhbnRfZm4uPGxvY2Fscz4uZnVuY5RLg0MI+IAA2A8SiAqUQwCUjAN2YWyUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flGgMdU5OaACMEF9tYWtlX2VtcHR5X2NlbGyUk5QpUpSFlHSUUpSMHGNsb3VkcGlja2xlLmNsb3VkcGlja2xlX2Zhc3SUjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIH2UfZQoaBhoDYwMX19xdWFsbmFtZV9flGgOjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgZjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9G8AaNuLrHhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Windows-10-10.0.19045-SP0 10.0.19045", "Python": "3.11.0", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cpu", "GPU Enabled": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -34.168033146858214, "std_reward": 11.844545943871326, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-02T22:26:31.825920"}
+{"mean_reward": -0.1999740525148809, "std_reward": 0.08756460738092221, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-06T08:16:37.111703"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317913de6cf942eb65e8716849923b7c48ed42940c0ecc33cb9758cfcdaf74a2
+oid sha256:e095ea3de42a514d268288d606e9d3608c7dcc5567218ce297aa3ccc38b4eb46
 size 2819