First A2C PandaReach model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PandaReachDense-v3
     metrics:
     - type: mean_reward
-      value: -0.19 +/- 0.09
+      value: -0.21 +/- 0.12
       name: mean_reward
       verified: false
 ---

a2c-PandaReachDense-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8102ea15d235d742f222137a022924094a13ec6e4eb40708a4e46d6b2574db33
+oid sha256:bda1fa24513d05cad980ffe1d6e455863bf1a8be82f7d54e7c6f233b9ab99064
 size 112504

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 0x00000196AAEFE830>",
+        "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x0000022B1FC92830>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc._abc_data object at 0x00000196AAEEF480>"
+        "_abc_impl": "<_abc._abc_data object at 0x0000022B1FC7F680>"
     },
     "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 0x00000196AAEFE830>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x00000196AAEEF480>"}, "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": 1764228127391446300, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-1.6744252   1.5439667  -2.0720146 ]\n [-0.12446891 -0.45808098 -0.17280626]\n [ 0.24946694  0.00397297  0.44408548]\n [ 0.24946694  0.00397297  0.44408548]]", "desired_goal": "[[-1.1426119   1.0234777  -0.9559828 ]\n [-1.3618484  -1.3625095  -0.9796127 ]\n [ 1.5761099  -0.9078676   0.73748696]\n [-1.1518598  -1.2202873  -1.3762106 ]]", "observation": "[[-1.6744252e+00  1.5439667e+00 -2.0720146e+00 -1.4163607e+00\n  -5.5487763e-02 -7.4684411e-01]\n [-1.2446891e-01 -4.5808098e-01 -1.7280626e-01 -1.8032771e+00\n  -1.6824226e+00 -1.3674178e+00]\n [ 2.4946694e-01  3.9729718e-03  4.4408548e-01  4.6722540e-01\n  -1.4797365e-03  3.7926614e-01]\n [ 2.4946694e-01  3.9729718e-03  4.4408548e-01  4.6722540e-01\n  -1.4797365e-03  3.7926614e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAAEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="}, "_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": "[[ 0.07168388  0.07633774  0.09071533]\n [ 0.04333336 -0.1228454   0.14048943]\n [-0.13755141 -0.13939029  0.1508826 ]\n [-0.03798345  0.12763537  0.03729711]]", "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": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": true, "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": "Windows-10-10.0.26100-SP0 10.0.26100", "Python": "3.10.19", "Stable-Baselines3": "2.0.0a4", "PyTorch": "2.9.1+cu128", "GPU Enabled": "True", "Numpy": "2.2.6", "Gym": "0.28.1"}}
+{"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 0x0000022B1FC92830>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x0000022B1FC7F680>"}, "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": 1764228127391446300, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-1.6744252   1.5439667  -2.0720146 ]\n [-0.12446891 -0.45808098 -0.17280626]\n [ 0.24946694  0.00397297  0.44408548]\n [ 0.24946694  0.00397297  0.44408548]]", "desired_goal": "[[-1.1426119   1.0234777  -0.9559828 ]\n [-1.3618484  -1.3625095  -0.9796127 ]\n [ 1.5761099  -0.9078676   0.73748696]\n [-1.1518598  -1.2202873  -1.3762106 ]]", "observation": "[[-1.6744252e+00  1.5439667e+00 -2.0720146e+00 -1.4163607e+00\n  -5.5487763e-02 -7.4684411e-01]\n [-1.2446891e-01 -4.5808098e-01 -1.7280626e-01 -1.8032771e+00\n  -1.6824226e+00 -1.3674178e+00]\n [ 2.4946694e-01  3.9729718e-03  4.4408548e-01  4.6722540e-01\n  -1.4797365e-03  3.7926614e-01]\n [ 2.4946694e-01  3.9729718e-03  4.4408548e-01  4.6722540e-01\n  -1.4797365e-03  3.7926614e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAAEBlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="}, "_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": "[[ 0.07168388  0.07633774  0.09071533]\n [ 0.04333336 -0.1228454   0.14048943]\n [-0.13755141 -0.13939029  0.1508826 ]\n [-0.03798345  0.12763537  0.03729711]]", "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": 0.95, "ent_coef": 0.0, "vf_coef": 0.5, "max_grad_norm": 0.5, "normalize_advantage": true, "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": "Windows-10-10.0.26100-SP0 10.0.26100", "Python": "3.10.19", "Stable-Baselines3": "2.0.0a4", "PyTorch": "2.9.1+cu128", "GPU Enabled": "True", "Numpy": "2.2.6", "Gym": "0.28.1"}}

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f527a56a09483fa32777a1205d9861f1372150f4d83acfc60815bb308051dbdd
+size 605269

results.json

@@ -1 +1 @@
-{"mean_reward": -0.1872473887167871, "std_reward": 0.0894087329207872, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-27T17:25:59.059712"}
+{"mean_reward": -0.20614526430144905, "std_reward": 0.11998399569455236, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-11-27T17:39:55.630697"}