Hugging Face's logo

Emptier8126
/
a2c-PandaReachDense-v3

Reinforcement Learning
stable-baselines3
PandaReachDense-v3
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
Emptier8126 commited on
Commit
c5f6ce2
·
verified ·
1 Parent(s): 63b0125

Initial commit

Browse files
Files changed (11) hide show
  1. README.md +1 -1
  2. a2c-PandaReachDense-v3.zip +2 -2
  3. a2c-PandaReachDense-v3/_stable_baselines3_version +1 -1
  4. a2c-PandaReachDense-v3/data +28 -27
  5. a2c-PandaReachDense-v3/policy.optimizer.pth +2 -2
  6. a2c-PandaReachDense-v3/policy.pth +2 -2
  7. a2c-PandaReachDense-v3/pytorch_variables.pth +2 -2
  8. a2c-PandaReachDense-v3/system_info.txt +7 -7
  9. config.json +1 -1
  10. results.json +1 -1
  11. vec_normalize.pkl +2 -2
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PandaReachDense-v3
17
  metrics:
18
  - type: mean_reward
19
- value: -0.24 +/- 0.10
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PandaReachDense-v3
17
  metrics:
18
  - type: mean_reward
19
+ value: -0.53 +/- 0.97
20
  name: mean_reward
21
  verified: false
22
  ---
a2c-PandaReachDense-v3.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b80eb22f77643b33323942bdd811d499b36695b5f948df49cff5bcc4ab42a56
3
- size 113957
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53ba3f1cb7ae36fe3506fa10f8121926155aabb8268e184db84e4adbccef3fb
3
+ size 114087
a2c-PandaReachDense-v3/_stable_baselines3_version CHANGED
@@ -1 +1 @@
1
- 2.3.2
 
1
+ 2.7.1
a2c-PandaReachDense-v3/data CHANGED
@@ -4,9 +4,9 @@
4
  ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__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 ",
7
- "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7c61c4007640>",
8
  "__abstractmethods__": "frozenset()",
9
- "_abc_impl": "<_abc._abc_data object at 0x7c61c3ffc300>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
@@ -24,25 +24,25 @@
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
- "start_time": 1730125041701015443,
28
- "learning_rate": 0.0007,
29
  "tensorboard_log": null,
30
  "_last_obs": {
31
  ":type:": "<class 'collections.OrderedDict'>",
32
- ":serialized:": "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",
33
- "achieved_goal": "[[ 0.22605373 0.00520874 0.37994626]\n [ 0.22605373 0.00520874 0.37994626]\n [ 0.31075343 0.14749774 -0.10145995]\n [-0.87031376 -0.01244623 -1.1872933 ]]",
34
- "desired_goal": "[[ 0.34197563 -1.0654825 -0.00348519]\n [-0.7532566 1.5016795 1.2857145 ]\n [ 0.69747895 0.09806406 -1.3192554 ]\n [-1.4856515 -0.1509514 -0.87858903]]",
35
- "observation": "[[ 0.22605373 0.00520874 0.37994626 0.45821258 0.00344506 0.37073612]\n [ 0.22605373 0.00520874 0.37994626 0.45821258 0.00344506 0.37073612]\n [ 0.31075343 0.14749774 -0.10145995 -0.05694795 0.12922 -1.4422816 ]\n [-0.87031376 -0.01244623 -1.1872933 -0.8170721 1.3674616 -0.9001049 ]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
39
- ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
40
  },
41
  "_last_original_obs": {
42
  ":type:": "<class 'collections.OrderedDict'>",
43
- ":serialized:": "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",
44
  "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]]",
45
- "desired_goal": "[[-0.04685763 0.0841266 0.13095136]\n [ 0.11253615 -0.1278927 0.299984 ]\n [-0.10562418 -0.11212344 0.02548239]\n [ 0.12644503 -0.00482882 0.06529864]]",
46
  "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]]"
47
  },
48
  "_episode_num": 0,
@@ -52,7 +52,7 @@
52
  "_stats_window_size": 100,
53
  "ep_info_buffer": {
54
  ":type:": "<class 'collections.deque'>",
55
- ":serialized:": "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"
56
  },
57
  "ep_success_buffer": {
58
  ":type:": "<class 'collections.deque'>",
@@ -60,7 +60,7 @@
60
  },
61
  "_n_updates": 50000,
62
  "n_steps": 5,
63
- "gamma": 0.99,
64
  "gae_lambda": 1.0,
65
  "ent_coef": 0.0,
66
  "vf_coef": 0.5,
@@ -69,44 +69,45 @@
69
  ":type:": "<class 'abc.ABCMeta'>",
70
  ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu",
71
  "__module__": "stable_baselines3.common.buffers",
72
- "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}",
73
  "__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 ",
74
- "__init__": "<function DictRolloutBuffer.__init__ at 0x7c61c40e2200>",
75
- "reset": "<function DictRolloutBuffer.reset at 0x7c61c40e2290>",
76
- "add": "<function DictRolloutBuffer.add at 0x7c61c40e2320>",
77
- "get": "<function DictRolloutBuffer.get at 0x7c61c40e23b0>",
78
- "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7c61c40e2440>",
79
  "__abstractmethods__": "frozenset()",
80
- "_abc_impl": "<_abc._abc_data object at 0x7c61c4109980>"
81
  },
82
  "rollout_buffer_kwargs": {},
83
  "normalize_advantage": false,
84
  "observation_space": {
85
  ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
86
- ":serialized:": "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",
87
- "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))])",
88
  "_shape": null,
89
  "dtype": null,
90
  "_np_random": null
91
  },
92
  "action_space": {
93
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
94
- ":serialized:": "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",
95
  "dtype": "float32",
96
- "bounded_below": "[ True True True]",
97
- "bounded_above": "[ True True True]",
98
  "_shape": [
99
  3
100
  ],
101
  "low": "[-1. -1. -1.]",
 
102
  "high": "[1. 1. 1.]",
 
103
  "low_repr": "-1.0",
104
  "high_repr": "1.0",
105
  "_np_random": null
106
  },
107
  "n_envs": 4,
108
  "lr_schedule": {
109
- ":type:": "<class 'function'>",
110
- ":serialized:": "gAWVkQMAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLA0sTQwx0AIgAfACDAYMBUwCUToWUjAVmbG9hdJSFlIwScHJvZ3Jlc3NfcmVtYWluaW5nlIWUjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lIwIPGxhbWJkYT6US2FDAgwAlIwOdmFsdWVfc2NoZWR1bGWUhZQpdJRSlH2UKIwLX19wYWNrYWdlX1+UjBhzdGFibGVfYmFzZWxpbmVzMy5jb21tb26UjAhfX25hbWVfX5SMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMCF9fZmlsZV9flIxJL3Vzci9sb2NhbC9saWIvcHl0aG9uMy4xMC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlGgAjBJfZnVuY3Rpb25fc2V0c3RhdGWUk5RoIX2UfZQoaBiMCDxsYW1iZGE+lIwMX19xdWFsbmFtZV9flIwhZ2V0X3NjaGVkdWxlX2ZuLjxsb2NhbHM+LjxsYW1iZGE+lIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoGYwHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlGgCKGgHKEsBSwBLAEsBSwFLE0MEiABTAJRoCSmMAV+UhZRoDowEZnVuY5RLhUMCBAGUjAN2YWyUhZQpdJRSlGgVTk5oHSlSlIWUdJRSlGgjaD59lH2UKGgYjARmdW5jlGgnjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlGgpfZRoK05oLE5oLWgZaC5OaC9oMUc/RvAGjbi6x4WUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwhZRSlIWUaEddlGhJfZR1hpSGUjAu"
 
111
  }
112
  }
 
4
  ":serialized:": "gAWVRQAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMG011bHRpSW5wdXRBY3RvckNyaXRpY1BvbGljeZSTlC4=",
5
  "__module__": "stable_baselines3.common.policies",
6
  "__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 ",
7
+ "__init__": "<function MultiInputActorCriticPolicy.__init__ at 0x7d181bcb16c0>",
8
  "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7d181bdfba00>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
 
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
+ "start_time": 1766668871157346115,
28
+ "learning_rate": 0.001,
29
  "tensorboard_log": null,
30
  "_last_obs": {
31
  ":type:": "<class 'collections.OrderedDict'>",
32
+ ":serialized:": "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",
33
+ "achieved_goal": "[[ 1.1553044 -1.331764 1.3529372 ]\n [-3.3816907 3.1419895 -2.5221794 ]\n [-2.4960146 -0.5359983 -2.098209 ]\n [ 0.32220373 0.03324365 0.46864423]]",
34
+ "desired_goal": "[[ 1.1147906 0.01475737 1.581023 ]\n [-1.1492437 0.9582857 -1.3738985 ]\n [-1.0513061 -1.2727948 -1.1349852 ]\n [-1.2464278 -0.5881276 -1.168052 ]]",
35
+ "observation": "[[ 1.1553044 -1.331764 1.3529372 1.009712 -0.93812203 1.455219 ]\n [-3.3816907 3.1419895 -2.5221794 1.6976252 0.64414686 1.62796 ]\n [-2.4960146 -0.5359983 -2.098209 1.2654606 1.0423188 1.0380588 ]\n [ 0.32220373 0.03324365 0.46864423 0.43520713 0.00455552 0.37437358]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
39
+ ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAAABlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksEhZSMAUOUdJRSlC4="
40
  },
41
  "_last_original_obs": {
42
  ":type:": "<class 'collections.OrderedDict'>",
43
+ ":serialized:": "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",
44
  "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]]",
45
+ "desired_goal": "[[ 0.07572927 0.06879537 0.07529301]\n [ 0.14515662 0.08935049 0.01842906]\n [ 0.14633146 -0.06526854 0.04217416]\n [ 0.12799037 -0.06162352 0.09144396]]",
46
  "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]]"
47
  },
48
  "_episode_num": 0,
 
52
  "_stats_window_size": 100,
53
  "ep_info_buffer": {
54
  ":type:": "<class 'collections.deque'>",
55
+ ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHv9GQo1DSgGuMAWyUSwSMAXSUR0CoiXQL3K0VdX2UKGgGR7/kAVwgkka/aAdLCWgIR0Coii2F36hydX2UKGgGR7/Vm4iHIp6QaAdLA2gIR0CoiYFTm4iHdX2UKGgGR7/VZH/cWTHKaAdLBGgIR0Coij5+hGpddX2UKGgGR7/lyrHU+cH4aAdLCWgIR0Coics6q815dX2UKGgGR7/RGFzuF6AwaAdLA2gIR0CoiYyV4X41dX2UKGgGR7/A3trsSkCWaAdLAmgIR0CoikiMHbAUdX2UKGgGR7/KIk7fYSQHaAdLA2gIR0CoidjSw4bTdX2UKGgGR7/UlnRLK3d9aAdLA2gIR0CoiZoqCpWFdX2UKGgGR7/TbcoH9m6HaAdLA2gIR0CoilOqFRHgdX2UKGgGR7/zIYNy5qdpaAdLD2gIR0Coihjej2zwdX2UKGgGR7/CmWt2cJ+laAdLAmgIR0CoieBj4HopdX2UKGgGR7+0MkQf6oETaAdLAmgIR0CoiaG8VYZEdX2UKGgGR7+8UtZmqYJFaAdLAmgIR0CoiiKd6LOzdX2UKGgGR7/T4AS39aUzaAdLA2gIR0CoimETg2qDdX2UKGgGR7/Bs7+1jRUnaAdLAmgIR0CoiatKIznBdX2UKGgGR7/OacZtNzsAaAdLA2gIR0Coie25paicdX2UKGgGR7++WE9Mbm2caAdLAmgIR0CoimhYvFm4dX2UKGgGR7/LrRjSXt0FaAdLA2gIR0Coii2JrLyMdX2UKGgGR7/SeQMhHLA6aAdLA2gIR0CoibZEc81XdX2UKGgGR7/QZw4sEq2CaAdLA2gIR0CoiftFrl/6dX2UKGgGR7/QU+s5n13/aAdLA2gIR0CoinY9gWrPdX2UKGgGR7/MhIOH31zyaAdLA2gIR0CoijtwR5C4dX2UKGgGR7+yV1Oj7ALzaAdLAmgIR0CoicCs4ku6dX2UKGgGR7/OT8pCrtE5aAdLA2gIR0CoigZs0pEydX2UKGgGR7+6mce8wpOOaAdLAmgIR0CoicfD1oQGdX2UKGgGR7/Xs0HhS9/SaAdLBWgIR0CoioqLjxTbdX2UKGgGR7/JEn9ehPCVaAdLA2gIR0CoidTo2XLNdX2UKGgGR7/YCfpUxVQzaAdLBGgIR0Coihd8Aq/edX2UKGgGR7/S8cMmWt2caAdLA2gIR0CoipWpAD7qdX2UKGgGR7/o4O2AoXsPaAdLCGgIR0CoilrZBcAzdX2UKGgGR7/FxUedTYNBaAdLAmgIR0CoiqUJfICEdX2UKGgGR7/MMcZLqUu+aAdLBGgIR0Coii9DIBBBdX2UKGgGR7/b3BYV6/qPaAdLBWgIR0CoifClJpWWdX2UKGgGR7/ILE1l5GBnaAdLA2gIR0Coim9f1HvudX2UKGgGR7+3Bi1Aqur7aAdLAmgIR0CoifiGvfTDdX2UKGgGR7/Sh+fAbhm5aAdLA2gIR0CoirIcBEKFdX2UKGgGR7/J97WuoxYaaAdLA2gIR0Coin1SGahIdX2UKGgGR7/SNHYpUgjhaAdLA2gIR0Coir+Sr5qNdX2UKGgGR7/PLidat9x7aAdLBGgIR0CoignYHxBmdX2UKGgGR7/TQ5myxA0LaAdLA2gIR0Coiohp5/smdX2UKGgGR7/j6Ae7tiQUaAdLB2gIR0Coikx5C4SZdX2UKGgGR7/MucMEzO5baAdLA2gIR0Cois0FbFCLdX2UKGgGR7/AHBUJfICEaAdLAmgIR0CoilYfGMn7dX2UKGgGR7/OYCyQgcLjaAdLA2gIR0Coite1rqMWdX2UKGgGR7/OKCQLeANHaAdLA2gIR0CoimDa4+bFdX2UKGgGR7/jAWrOqvNeaAdLB2gIR0CoiqaltTDPdX2UKGgGR7/SVPN3W4EwaAdLA2gIR0Coim5UDMePdX2UKGgGR7/bIUJv5xioaAdLBGgIR0CoiukJjUd8dX2UKGgGR7/QsQNCqp97aAdLA2gIR0CoirGwaBI4dX2UKGgGR7/LXxvvSc9XaAdLA2gIR0CoivX5vcagdX2UKGgGR7/ZaePJaJQ+aAdLBGgIR0Coin8V58jSdX2UKGgGR7/JgJkXk5p8aAdLA2gIR0Coir67dznzdX2UKGgGR7+oKx9oexOdaAdLAWgIR0CoioLbHp8ndX2UKGgGR7/Skadc0LtvaAdLA2gIR0CoiwDnmq5tdX2UKGgGR7/cg7o0Q9RraAdLBGgIR0Cois+9alk6dX2UKGgGR7/QRgqmTC+DaAdLBGgIR0CoipPdVNpNdX2UKGgGR7/T7HQyAQQMaAdLA2gIR0Coiw6TfR/mdX2UKGgGR7/CngpBomG/aAdLAmgIR0Coitc9Oh0ydX2UKGgGR7/TI4VARkEtaAdLA2gIR0CoixlNcnmadX2UKGgGR7/VTxG2CuloaAdLBGgIR0CoiqKFh5PedX2UKGgGR7++BpYcNpdsaAdLAmgIR0CoiyNIK+i8dX2UKGgGR7/U9Cu2Zy+6aAdLBWgIR0CoiuwB5ooNdX2UKGgGR7/KNFz+3pfQaAdLA2gIR0CoirANPP9ldX2UKGgGR7/Thpg1FYuCaAdLA2gIR0Coiy6pgkTpdX2UKGgGR7/Tms/6fra/aAdLA2gIR0CoivonKGL2dX2UKGgGR7/Nsa86FM7EaAdLA2gIR0Coir43m3fAdX2UKGgGR7+/PTodMj/uaAdLAmgIR0CoisVSOzY3dX2UKGgGR7/VvW6K+BYnaAdLBWgIR0Coi0OxKQJYdX2UKGgGR7/BrTpgTh5xaAdLAmgIR0CoiszcAR02dX2UKGgGR8AELsWweNkwaAdLIGgIR0Coio4oJAt4dX2UKGgGR7+33JxNqQA/aAdLAmgIR0Coi01w5vLpdX2UKGgGR7/csk6cRUWEaAdLBmgIR0CoixKtga3rdX2UKGgGR7/Jb8m8dxQ0aAdLA2gIR0Coitpobn5jdX2UKGgGR7++7I1cdHUdaAdLAmgIR0CoixonBtUGdX2UKGgGR7/cjh1klNUPaAdLBGgIR0Coip9aUzKtdX2UKGgGR7/cTVUdaMaTaAdLBGgIR0Coi16e5Fw2dX2UKGgGR7/TgZjx0+1SaAdLA2gIR0Coiue3hGYsdX2UKGgGR7+0lOXVsk6caAdLAmgIR0CoiqkFfReDdX2UKGgGR7/LMg2ZRbbDaAdLA2gIR0CoiyeNT987dX2UKGgGR7/LcKPXCj1xaAdLA2gIR0CoivKOtGNJdX2UKGgGR7/Q3M6ij+JhaAdLA2gIR0CoirQztTkydX2UKGgGR7/WIxxkupS8aAdLBWgIR0Coi3T/ACXAdX2UKGgGR7/Y8UEgW8AaaAdLBGgIR0CoizqLKmsOdX2UKGgGR7/AIu5BkZrIaAdLAmgIR0CoisAGbCrMdX2UKGgGR7/OeDFqBVdYaAdLA2gIR0CoiwKWcBludX2UKGgGR7/OEDhcZ9/jaAdLA2gIR0Coi4CWu5jIdX2UKGgGR7/TC8e0Xxe+aAdLA2gIR0Coisrgflp5dX2UKGgGR7/TZssQNCqqaAdLBGgIR0Coi0lsxfv4dX2UKGgGR7/VPKuB+WnkaAdLA2gIR0Coiw2PLgXNdX2UKGgGR7/D238XN1QqaAdLAmgIR0CoitR/d69kdX2UKGgGR7/SBz3h4t6HaAdLA2gIR0Coi437k4m1dX2UKGgGR7/HHzYmLLpzaAdLA2gIR0Coixp3PiT/dX2UKGgGR7/EKJEYwZflaAdLAmgIR0CoitvHDJlrdX2UKGgGR7+m+CbtqpLmaAdLAWgIR0Coix5u63AmdX2UKGgGR7/QtsvZh8YyaAdLA2gIR0Coi5kMspXqdX2UKGgGR7+5lK9PDYRNaAdLAmgIR0Coiyh42S+ydX2UKGgGR7/Nrqt5le4TaAdLA2gIR0CoiunXd0q6dX2UKGgGR7/MTt9hJAdGaAdLA2gIR0Coi6bqY7aJdX2UKGgGR7/ZuZ1FH8TBaAdLBGgIR0CoivkmY0EYdWUu"
56
  },
57
  "ep_success_buffer": {
58
  ":type:": "<class 'collections.deque'>",
 
60
  },
61
  "_n_updates": 50000,
62
  "n_steps": 5,
63
+ "gamma": 0.95,
64
  "gae_lambda": 1.0,
65
  "ent_coef": 0.0,
66
  "vf_coef": 0.5,
 
69
  ":type:": "<class 'abc.ABCMeta'>",
70
  ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu",
71
  "__module__": "stable_baselines3.common.buffers",
72
+ "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': dict[str, tuple[int, ...]], 'observations': dict[str, numpy.ndarray]}",
73
  "__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 ",
74
+ "__init__": "<function DictRolloutBuffer.__init__ at 0x7d181bc2e3e0>",
75
+ "reset": "<function DictRolloutBuffer.reset at 0x7d181bc2e480>",
76
+ "add": "<function DictRolloutBuffer.add at 0x7d181bc2e5c0>",
77
+ "get": "<function DictRolloutBuffer.get at 0x7d181bc2e660>",
78
+ "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7d181bc2e700>",
79
  "__abstractmethods__": "frozenset()",
80
+ "_abc_impl": "<_abc._abc_data object at 0x7d181bdea140>"
81
  },
82
  "rollout_buffer_kwargs": {},
83
  "normalize_advantage": false,
84
  "observation_space": {
85
  ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
86
+ ":serialized:": "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",
87
+ "spaces": "{'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)}",
88
  "_shape": null,
89
  "dtype": null,
90
  "_np_random": null
91
  },
92
  "action_space": {
93
  ":type:": "<class 'gymnasium.spaces.box.Box'>",
94
+ ":serialized:": "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",
95
  "dtype": "float32",
 
 
96
  "_shape": [
97
  3
98
  ],
99
  "low": "[-1. -1. -1.]",
100
+ "bounded_below": "[ True True True]",
101
  "high": "[1. 1. 1.]",
102
+ "bounded_above": "[ True True True]",
103
  "low_repr": "-1.0",
104
  "high_repr": "1.0",
105
  "_np_random": null
106
  },
107
  "n_envs": 4,
108
  "lr_schedule": {
109
+ ":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>",
110
+ ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/UGJN0vGp/HNic2Iu",
111
+ "value_schedule": "ConstantSchedule(val=0.001)"
112
  }
113
  }
a2c-PandaReachDense-v3/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37c13064d4ff6faf1b5acb6d9bde69368018f6a03be5288b46a3253c42ab88f0
3
- size 48456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29560748f1141589fb421c071157533c4e1075c3ad7cfae11af454badb51b32c
3
+ size 48917
a2c-PandaReachDense-v3/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cfd00de355b9cbeda48faf4763462bf45b40ec075bfab2d9e46930859ffa83d
3
- size 46447
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d83c95c6ad3e6026ffe74c942671803688897c3774eeaaa017c4ec8b7ffe616
3
+ size 46780
a2c-PandaReachDense-v3/pytorch_variables.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
3
- size 864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07c7431cf6005e7d8f367d79e995f63e2f9b981a37e3437b795d058f9af4308b
3
+ size 1261
a2c-PandaReachDense-v3/system_info.txt CHANGED
@@ -1,9 +1,9 @@
1
- - OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024
2
- - Python: 3.10.12
3
- - Stable-Baselines3: 2.3.2
4
- - PyTorch: 2.5.0+cu121
5
  - GPU Enabled: True
6
- - Numpy: 1.26.4
7
- - Cloudpickle: 3.1.0
8
- - Gymnasium: 0.29.1
9
  - OpenAI Gym: 0.25.2
 
1
+ - OS: Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct 2 10:42:05 UTC 2025
2
+ - Python: 3.12.12
3
+ - Stable-Baselines3: 2.7.1
4
+ - PyTorch: 2.9.0+cu126
5
  - GPU Enabled: True
6
+ - Numpy: 2.0.2
7
+ - Cloudpickle: 3.1.2
8
+ - Gymnasium: 1.2.2
9
  - OpenAI Gym: 0.25.2
config.json CHANGED
@@ -1 +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 0x7c61c4007640>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c61c3ffc300>"}, "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": 1730125041701015443, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.22605373 0.00520874 0.37994626]\n [ 0.22605373 0.00520874 0.37994626]\n [ 0.31075343 0.14749774 -0.10145995]\n [-0.87031376 -0.01244623 -1.1872933 ]]", "desired_goal": "[[ 0.34197563 -1.0654825 -0.00348519]\n [-0.7532566 1.5016795 1.2857145 ]\n [ 0.69747895 0.09806406 -1.3192554 ]\n [-1.4856515 -0.1509514 -0.87858903]]", "observation": "[[ 0.22605373 0.00520874 0.37994626 0.45821258 0.00344506 0.37073612]\n [ 0.22605373 0.00520874 0.37994626 0.45821258 0.00344506 0.37073612]\n [ 0.31075343 0.14749774 -0.10145995 -0.05694795 0.12922 -1.4422816 ]\n [-0.87031376 -0.01244623 -1.1872933 -0.8170721 1.3674616 -0.9001049 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.04685763 0.0841266 0.13095136]\n [ 0.11253615 -0.1278927 0.299984 ]\n [-0.10562418 -0.11212344 0.02548239]\n [ 0.12644503 -0.00482882 0.06529864]]", "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_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, "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 0x7c61c40e2200>", "reset": "<function DictRolloutBuffer.reset at 0x7c61c40e2290>", "add": "<function DictRolloutBuffer.add at 0x7c61c40e2320>", "get": "<function DictRolloutBuffer.get at 0x7c61c40e23b0>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7c61c40e2440>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c61c4109980>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Thu Jun 27 21:05:47 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.3.2", "PyTorch": "2.5.0+cu121", "GPU Enabled": "True", "Numpy": "1.26.4", "Cloudpickle": "3.1.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
 
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 0x7d181bcb16c0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d181bdfba00>"}, "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": 1766668871157346115, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 1.1553044 -1.331764 1.3529372 ]\n [-3.3816907 3.1419895 -2.5221794 ]\n [-2.4960146 -0.5359983 -2.098209 ]\n [ 0.32220373 0.03324365 0.46864423]]", "desired_goal": "[[ 1.1147906 0.01475737 1.581023 ]\n [-1.1492437 0.9582857 -1.3738985 ]\n [-1.0513061 -1.2727948 -1.1349852 ]\n [-1.2464278 -0.5881276 -1.168052 ]]", "observation": "[[ 1.1553044 -1.331764 1.3529372 1.009712 -0.93812203 1.455219 ]\n [-3.3816907 3.1419895 -2.5221794 1.6976252 0.64414686 1.62796 ]\n [-2.4960146 -0.5359983 -2.098209 1.2654606 1.0423188 1.0380588 ]\n [ 0.32220373 0.03324365 0.46864423 0.43520713 0.00455552 0.37437358]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVeAAAAAAAAACME251bXB5Ll9jb3JlLm51bWVyaWOUjAtfZnJvbWJ1ZmZlcpSTlCiWBAAAAAAAAAAAAAABlIwFbnVtcHmUjAVkdHlwZZSTlIwCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////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": "[[ 0.07572927 0.06879537 0.07529301]\n [ 0.14515662 0.08935049 0.01842906]\n [ 0.14633146 -0.06526854 0.04217416]\n [ 0.12799037 -0.06162352 0.09144396]]", "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_n_updates": 50000, "n_steps": 5, "gamma": 0.95, "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': dict[str, tuple[int, ...]], 'observations': 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 0x7d181bc2e3e0>", "reset": "<function DictRolloutBuffer.reset at 0x7d181bc2e480>", "add": "<function DictRolloutBuffer.add at 0x7d181bc2e5c0>", "get": "<function DictRolloutBuffer.get at 0x7d181bc2e660>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7d181bc2e700>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d181bdea140>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "{'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", "_shape": [3], "low": "[-1. -1. -1.]", "bounded_below": "[ True True True]", "high": "[1. 1. 1.]", "bounded_above": "[ True True True]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'stable_baselines3.common.utils.FloatSchedule'>", ":serialized:": "gAWVeQAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi51dGlsc5SMDUZsb2F0U2NoZWR1bGWUk5QpgZR9lIwOdmFsdWVfc2NoZWR1bGWUaACMEENvbnN0YW50U2NoZWR1bGWUk5QpgZR9lIwDdmFslEc/UGJN0vGp/HNic2Iu", "value_schedule": "ConstantSchedule(val=0.001)"}, "system_info": {"OS": "Linux-6.6.105+-x86_64-with-glibc2.35 # 1 SMP Thu Oct 2 10:42:05 UTC 2025", "Python": "3.12.12", "Stable-Baselines3": "2.7.1", "PyTorch": "2.9.0+cu126", "GPU Enabled": "True", "Numpy": "2.0.2", "Cloudpickle": "3.1.2", "Gymnasium": "1.2.2", "OpenAI Gym": "0.25.2"}}
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -0.23694471782073379, "std_reward": 0.10303375494362468, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-10-28T14:57:15.306694"}
 
1
+ {"mean_reward": -0.5313212290406227, "std_reward": 0.9736758045334537, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-25T14:03:31.977837"}
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d24fa5eaa3c797ccf0fd897050b64e2b21c65698e56dd42eb0e9a84c86a3e4e
3
- size 2646
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43e00f6f871e69eb439b0742155373920f494ba34b173afc7f8e24e2e6a58cb3
3
+ size 2644