Train with 5_000_000 steps

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.26 +/- 0.08
+      value: -0.21 +/- 0.11
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1b935f7b20cef5dc2f47901ff8cca725f302b54f2a1833cdb7f28a2ae54aca2
-size 110387
+oid sha256:7f614a2ff136de64d23c5457182f9da6d25eb036d69ca40053f2036b34cd2d9e
+size 110268

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 0x7f231654b1c0>",
+        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7f1500e631c0>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f23165504c0>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f1500e68680>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -19,30 +19,30 @@
             "weight_decay": 0
         }
     },
-    "num_timesteps": 1000000,
-    "_total_timesteps": 1000000,
+    "num_timesteps": 5000000,
+    "_total_timesteps": 5000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": 1710690151131069050,
+    "start_time": 1710693915893857757,
     "learning_rate": 0.0007,
     "tensorboard_log": null,
     "_last_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "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",
-        "achieved_goal": "[[ 9.3710601e-01  4.0367842e-01  2.4881473e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01]]",
-        "desired_goal": "[[ 1.136349    0.3523281  -0.42099562]\n [ 1.4019009  -0.83463615 -1.2476281 ]\n [-0.32124656 -0.43861663  0.3914814 ]\n [ 0.9245776  -0.84981155 -1.390559  ]]",
-        "observation": "[[ 9.3710601e-01  4.0367842e-01  2.4881473e-01  1.5713389e+00\n   1.6212766e+00 -1.1560352e+00]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01  4.6396786e-01\n   5.5499998e-04  3.7569594e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01  4.6396786e-01\n   5.5499998e-04  3.7569594e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01  4.6396786e-01\n   5.5499998e-04  3.7569594e-01]]"
+        ":serialized:": "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",
+        "achieved_goal": "[[-1.5472001  -1.010874   -1.2088292 ]\n [ 0.3242649  -0.02297759  0.45474702]\n [-0.08497681 -0.545043   -0.24493209]\n [ 0.3242649  -0.02297759  0.45474702]]",
+        "desired_goal": "[[-0.9784099  -0.449471    0.07078814]\n [ 0.07759214 -0.3991155  -0.1471956 ]\n [-0.36612976 -0.71449536 -1.4383343 ]\n [ 0.19070671  0.9415055   0.9052434 ]]",
+        "observation": "[[-1.5472001  -1.010874   -1.2088292  -1.2333245   0.07443594 -0.27640918]\n [ 0.3242649  -0.02297759  0.45474702  0.49100387 -0.00877907  0.39452156]\n [-0.08497681 -0.545043   -0.24493209 -1.7974333  -1.6812764  -1.3623828 ]\n [ 0.3242649  -0.02297759  0.45474702  0.49100387 -0.00877907  0.39452156]]"
     },
     "_last_episode_starts": {
         ":type:": "<class 'numpy.ndarray'>",
-        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAAGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
     },
     "_last_original_obs": {
         ":type:": "<class 'collections.OrderedDict'>",
-        ":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAA6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAA+PLqvKIbA74MFm4+30H6PPuKrT3V5J497+4VPtVQyz0YD5M+LKbCvTy/FD5JwR0+lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWYAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LBEsGhpRoEnSUUpR1Lg==",
+        ":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": "[[-0.02868031 -0.1280351   0.23250598]\n [ 0.03054899  0.08473774  0.0775849 ]\n [ 0.14641927  0.09927527  0.28722453]\n [-0.09504351  0.14526075  0.15405764]]",
+        "desired_goal": "[[ 0.045141    0.07113054  0.16172004]\n [ 0.13018587 -0.02770718  0.27832267]\n [-0.10077076 -0.1289667   0.1038551 ]\n [-0.00490848 -0.11308774  0.03392871]]",
         "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,
@@ -52,13 +52,13 @@
     "_stats_window_size": 100,
     "ep_info_buffer": {
         ":type:": "<class 'collections.deque'>",
-        ":serialized:": "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"
+        ":serialized:": "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"
     },
     "ep_success_buffer": {
         ":type:": "<class 'collections.deque'>",
         ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
     },
-    "_n_updates": 50000,
+    "_n_updates": 250000,
     "observation_space": {
         ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
         ":serialized:": "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",
@@ -95,13 +95,13 @@
         "__module__": "stable_baselines3.common.buffers",
         "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}",
         "__doc__": "\n    Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n    Extends the RolloutBuffer to use dictionary observations\n\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to Monte-Carlo advantage estimate when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ",
-        "__init__": "<function DictRolloutBuffer.__init__ at 0x7f23166f8ee0>",
-        "reset": "<function DictRolloutBuffer.reset at 0x7f23166f8f70>",
-        "add": "<function DictRolloutBuffer.add at 0x7f23166f9000>",
-        "get": "<function DictRolloutBuffer.get at 0x7f23166f9090>",
-        "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7f23166f9120>",
+        "__init__": "<function DictRolloutBuffer.__init__ at 0x7f1500e14ee0>",
+        "reset": "<function DictRolloutBuffer.reset at 0x7f1500e14f70>",
+        "add": "<function DictRolloutBuffer.add at 0x7f1500e15000>",
+        "get": "<function DictRolloutBuffer.get at 0x7f1500e15090>",
+        "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7f1500e15120>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x7f23166ed900>"
+        "_abc_impl": "<_abc._abc_data object at 0x7f1500e09840>"
     },
     "rollout_buffer_kwargs": {},
     "normalize_advantage": false,

a2c-PandaReachDense-v3/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dae94a1174195405091a2d55dc5bfd67708561cf5be76c58deae1e319599b9ce
+oid sha256:22e3e98b5c46cbacd3b693f6196df2cdc3c52f1ee79c15248f27f8adcb36834b
 size 45167

a2c-PandaReachDense-v3/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76514d6c3d522184998ce405dc2d9a0316df54d4ec644464285e4d805b055cf9
+oid sha256:6847e73104f647d56ce86a90f425c228329d894b3592432ddd498ea5298e00a4
 size 46447

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 0x7f231654b1c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f23165504c0>"}, "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": 1710690151131069050, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 9.3710601e-01  4.0367842e-01  2.4881473e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01]]", "desired_goal": "[[ 1.136349    0.3523281  -0.42099562]\n [ 1.4019009  -0.83463615 -1.2476281 ]\n [-0.32124656 -0.43861663  0.3914814 ]\n [ 0.9245776  -0.84981155 -1.390559  ]]", "observation": "[[ 9.3710601e-01  4.0367842e-01  2.4881473e-01  1.5713389e+00\n   1.6212766e+00 -1.1560352e+00]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01  4.6396786e-01\n   5.5499998e-04  3.7569594e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01  4.6396786e-01\n   5.5499998e-04  3.7569594e-01]\n [ 2.1114476e-01 -5.3300825e-04  4.1360956e-01  4.6396786e-01\n   5.5499998e-04  3.7569594e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.02868031 -0.1280351   0.23250598]\n [ 0.03054899  0.08473774  0.0775849 ]\n [ 0.14641927  0.09927527  0.28722453]\n [-0.09504351  0.14526075  0.15405764]]", "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, "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, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n    Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n    Extends the RolloutBuffer to use dictionary observations\n\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to Monte-Carlo advantage estimate when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function DictRolloutBuffer.__init__ at 0x7f23166f8ee0>", "reset": "<function DictRolloutBuffer.reset at 0x7f23166f8f70>", "add": "<function DictRolloutBuffer.add at 0x7f23166f9000>", "get": "<function DictRolloutBuffer.get at 0x7f23166f9090>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7f23166f9120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f23166ed900>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.0-91-generic-x86_64-with-glibc2.35 # 101-Ubuntu SMP Tue Nov 14 13:30:08 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.2+cu118", "GPU Enabled": "True", "Numpy": "1.24.1", "Cloudpickle": "3.0.0", "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 0x7f1500e631c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f1500e68680>"}, "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": 5000000, "_total_timesteps": 5000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1710693915893857757, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-1.5472001  -1.010874   -1.2088292 ]\n [ 0.3242649  -0.02297759  0.45474702]\n [-0.08497681 -0.545043   -0.24493209]\n [ 0.3242649  -0.02297759  0.45474702]]", "desired_goal": "[[-0.9784099  -0.449471    0.07078814]\n [ 0.07759214 -0.3991155  -0.1471956 ]\n [-0.36612976 -0.71449536 -1.4383343 ]\n [ 0.19070671  0.9415055   0.9052434 ]]", "observation": "[[-1.5472001  -1.010874   -1.2088292  -1.2333245   0.07443594 -0.27640918]\n [ 0.3242649  -0.02297759  0.45474702  0.49100387 -0.00877907  0.39452156]\n [-0.08497681 -0.545043   -0.24493209 -1.7974333  -1.6812764  -1.3623828 ]\n [ 0.3242649  -0.02297759  0.45474702  0.49100387 -0.00877907  0.39452156]]"}, "_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": "[[ 0.045141    0.07113054  0.16172004]\n [ 0.13018587 -0.02770718  0.27832267]\n [-0.10077076 -0.1289667   0.1038551 ]\n [-0.00490848 -0.11308774  0.03392871]]", "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": 250000, "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, "n_steps": 5, "gamma": 0.99, "gae_lambda": 1.0, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n    Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n    Extends the RolloutBuffer to use dictionary observations\n\n    It corresponds to ``buffer_size`` transitions collected\n    using the current policy.\n    This experience will be discarded after the policy update.\n    In order to use PPO objective, we also store the current value of each state\n    and the log probability of each taken action.\n\n    The term rollout here refers to the model-free notion and should not\n    be used with the concept of rollout used in model-based RL or planning.\n    Hence, it is only involved in policy and value function training but not action selection.\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 gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n        Equivalent to Monte-Carlo advantage estimate when set to 1.\n    :param gamma: Discount factor\n    :param n_envs: Number of parallel environments\n    ", "__init__": "<function DictRolloutBuffer.__init__ at 0x7f1500e14ee0>", "reset": "<function DictRolloutBuffer.reset at 0x7f1500e14f70>", "add": "<function DictRolloutBuffer.add at 0x7f1500e15000>", "get": "<function DictRolloutBuffer.get at 0x7f1500e15090>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7f1500e15120>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f1500e09840>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.0-91-generic-x86_64-with-glibc2.35 # 101-Ubuntu SMP Tue Nov 14 13:30:08 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.1.2+cu118", "GPU Enabled": "True", "Numpy": "1.24.1", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}

results.json

@@ -1 +1 @@
-{"mean_reward": -0.25629245974123477, "std_reward": 0.08482671807502236, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-17T17:12:57.627979"}
+{"mean_reward": -0.20864116493612528, "std_reward": 0.11458533921482136, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-17T20:16:49.000470"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9011b1efa2b066b6da59132d2d4ca6df12bba4aaf3496d3bd02570eb685307
+oid sha256:19a208817f1dabad3da474ee15a00b8b89706b2dfe185e444a5ebf7d8a54b920
 size 2720