Hugging Face's logo

MatteoColavita
/
a2c-PandaReachDense-v3

Reinforcement Learning
stable-baselines3
PandaReachDense-v3
deep-reinforcement-learning
Eval Results
Model card Files Community
1
MatteoColavita commited on
Commit
0233f79
•
1 Parent(s): 978c1af

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +1 -1
  2. a2c-PandaReachDense-v3.zip +1 -1
  3. a2c-PandaReachDense-v3/data +10 -10
  4. a2c-PandaReachDense-v3/policy.optimizer.pth +1 -1
  5. a2c-PandaReachDense-v3/policy.pth +1 -1
  6. config.json +1 -1
  7. replay.mp4 +0 -0
  8. results.json +1 -1
  9. 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: -15.94 +/- 2.62
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PandaReachDense-v3
17
  metrics:
18
  - type: mean_reward
19
+ value: -0.26 +/- 0.13
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 sha256:0f5691c329e3705bfa74681a6456e837011a4a493f1590ef68ec33ffda14c5c9
3
  size 106831
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d73cbb78861839e759438f5ade1bc04c00566af79bd1f0b7e6b8edc13a2c7b0c
3
  size 106831
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 0x7d83a7aedc60>",
8
  "__abstractmethods__": "frozenset()",
9
- "_abc_impl": "<_abc._abc_data object at 0x7d83a7af0a00>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
@@ -24,15 +24,15 @@
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
- "start_time": 1691435117619413130,
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": "[[-4.349957 -0.50133437 -2.4799817 ]\n [ 0.5486673 -0.40149376 0.6618299 ]\n [ 0.5515472 0.4203138 0.66129667]\n [-0.4125532 -0.45368677 0.3317958 ]]",
34
- "desired_goal": "[[-1.5457624 0.15444034 -0.8485371 ]\n [ 1.2425882 -0.3560116 1.5531467 ]\n [ 0.74012655 0.10647513 1.4478446 ]\n [-0.60608494 -1.225225 0.0995459 ]]",
35
- "observation": "[[-4.349957 -0.50133437 -2.4799817 -0.6413411 -1.6428975 1.5209249 ]\n [ 0.5486673 -0.40149376 0.6618299 1.6701304 -1.5866346 1.117392 ]\n [ 0.5515472 0.4203138 0.66129667 1.6294065 1.5228907 1.0934463 ]\n [-0.4125532 -0.45368677 0.3317958 -0.7524077 -1.6643292 0.6936233 ]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
@@ -40,9 +40,9 @@
40
  },
41
  "_last_original_obs": {
42
  ":type:": "<class 'collections.OrderedDict'>",
43
- ":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAA6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAAjUj0vS8IFL7UMyA9uYcKvixoXj3TQkY+ZAwOvlygyr3tXGo+xrssPaR1d72SXG0+lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWYAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LBEsGhpRoEnSUUpR1Lg==",
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": "[[-0.119279 -0.14456247 0.03911193]\n [-0.13528337 0.05429856 0.19361429]\n [-0.13871914 -0.09893867 0.22887011]\n [ 0.04217126 -0.06041493 0.23179844]]",
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:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHv9DbFjurp7mMAWyUSwOMAXSUR0ClA4ryMDOkdX2UKGgGR7/TybhFVktmaAdLBGgIR0ClA010cOsldX2UKGgGR7/lPfsNUfgaaAdLB2gIR0ClAxaZQYUGdX2UKGgGR7/Q/5+H8CPqaAdLA2gIR0ClAtvqLS/kdX2UKGgGR7/br1M/QjUvaAdLBGgIR0ClA1/ra/RFdX2UKGgGR7/B5zHS4OMEaAdLAmgIR0ClAyE+gUUPdX2UKGgGR7/QHaews5GSaAdLA2gIR0ClAusEidJ8dX2UKGgGR7/gAksz2vjfaAdLBmgIR0ClA6aqS5iFdX2UKGgGR7/RdUsFt8/maAdLA2gIR0ClA20fgaWHdX2UKGgGR7/NDKoybhFWaAdLA2gIR0ClAy5ssQNDdX2UKGgGR7+9cLSeAd4naAdLAmgIR0ClAvO3UhFFdX2UKGgGR7+3pfQa72+PaAdLAmgIR0ClA3fL9uP4dX2UKGgGR7/cNXo1UEPlaAdLBGgIR0ClA7mDtgKGdX2UKGgGR7+VB2OhkAggaAdLAWgIR0ClA3v+4smOdX2UKGgGR7/SsunMt9QXaAdLA2gIR0ClAz04BFNMdX2UKGgGR7/SU3n6l+EzaAdLA2gIR0ClAwKZUkv9dX2UKGgGR7+94wAU+LWJaAdLAmgIR0ClA4UornTzdX2UKGgGR7+3Ho5ggHNYaAdLAmgIR0ClA0Z1eSjhdX2UKGgGR7+k7IT4+KTCaAdLAWgIR0ClA4nd43WGdX2UKGgGR7/Tqur6tT1kaAdLBGgIR0ClAxcPe54GdX2UKGgGR7/bA6dUbT+eaAdLBWgIR0ClA9LMs6JZdX2UKGgGR7/So2XLNfPYaAdLA2gIR0ClA1aCDmKZdX2UKGgGR7/aTwDvE0iyaAdLBGgIR0ClA59OymhudX2UKGgGR7/CiY9gWrOraAdLA2gIR0ClA2UOEug6dX2UKGgGR7/PdX1anrIHaAdLBGgIR0ClAypUo8ZDdX2UKGgGR7/TUb1h9b5eaAdLBGgIR0ClA+pPhybQdX2UKGgGR7+9ZHNHH3lCaAdLAmgIR0ClA62/i5uqdX2UKGgGR7/BnB+F10T2aAdLAmgIR0ClAzkAxSHedX2UKGgGR7+67Ackt29taAdLAmgIR0ClA7bkn1FpdX2UKGgGR7/bOX3QD3dsaAdLBGgIR0ClA3waisXBdX2UKGgGR7/AarFOwgTzaAdLAmgIR0ClA0FmWdEtdX2UKGgGR7/bsbedkJ8faAdLBmgIR0ClBAeZXuE3dX2UKGgGR7/SZ6Uqx1PnaAdLA2gIR0ClA1B55Z8sdX2UKGgGR7/X91loUSIyaAdLBGgIR0ClA4/KQq7RdX2UKGgGR7/SRnOB19v1aAdLA2gIR0ClA11UMoc8dX2UKGgGR7/YPIGQjlgdaAdLBWgIR0ClBB9D6WPcdX2UKGgGR7/aaSs8xKxtaAdLBGgIR0ClA6MEzO5bdX2UKGgGR7/Onn+yZ8a5aAdLA2gIR0ClA2yCWeH0dX2UKGgGR7/KEaESM98raAdLA2gIR0ClBCwdCE6DdX2UKGgGR7/EjC53C9AYaAdLA2gIR0ClA3sSK3uvdX2UKGgGR7+65LAYYR/WaAdLAmgIR0ClBDa5f+judX2UKGgGR7/m4Qrc0tROaAdLCGgIR0ClA8eGfwqidX2UKGgGR7+lpPAO8TSLaAdLAWgIR0ClA85e7cwhdX2UKGgGR7/k0aIeo1k2aAdLB2gIR0ClBFhmwqy4dX2UKGgGR7/ms4LkS26TaAdLCGgIR0ClA6Fv60pmdX2UKGgGR7/eoW56MR6GaAdLBGgIR0ClA+CvX9R8dX2UKGgGR7/NJRO1v2oOaAdLA2gIR0ClBGgwPAfudX2UKGgGR7/Mbn5i3G4raAdLA2gIR0ClA7D5KvmpdX2UKGgGR7/RrDZUT+NtaAdLA2gIR0ClA+/QBxPwdX2UKGgGR8AC0sz2vjffaAdLGmgIR0ClBDNCZ4OddX2UKGgGR7/Hd9lVcUudaAdLA2gIR0ClBHUl7dBTdX2UKGgGR7+/b7CSA6MjaAdLAmgIR0ClBD3mFJxvdX2UKGgGR7/T5dnkDIRzaAdLBGgIR0ClBAMcZLqVdX2UKGgGR7/cucMEzO5baAdLBWgIR0ClA8h06o2odX2UKGgGR7/R8D0UXYUWaAdLA2gIR0ClBIQPI4lydX2UKGgGR7/B/Aj6eoUBaAdLAmgIR0ClBEaRISUUdX2UKGgGR7/B0Rvm5lOHaAdLAmgIR0ClBAuNHYpVdX2UKGgGR7+6V/tpmEoOaAdLAmgIR0ClBE6v7m+1dX2UKGgGR7/JEGZ/kNnXaAdLA2gIR0ClA9T1kDp1dX2UKGgGR7/QkZJkGzKLaAdLA2gIR0ClBJL4N7SidX2UKGgGR7/Q0Y0l7dBTaAdLA2gIR0ClBBpeeFtbdX2UKGgGR7/QY/Vy3kPuaAdLA2gIR0ClBF2IGhVVdX2UKGgGR7/JLZi/fwZwaAdLA2gIR0ClA+PaDf3wdX2UKGgGR7/PaTOgQHzIaAdLA2gIR0ClBJ+HSF4+dX2UKGgGR7/GfNiYsunNaAdLAmgIR0ClBKoW56MSdX2UKGgGR7/KG/N7jT8YaAdLA2gIR0ClBGykCV8kdX2UKGgGR7/Rqnm7rcCYaAdLBGgIR0ClBC3R5TqCdX2UKGgGR7+3wob4rSVoaAdLAmgIR0ClBHUB4lhPdX2UKGgGR7/WhRIjGDL9aAdLBWgIR0ClA/uaOPvKdX2UKGgGR7/FjOs1baAXaAdLA2gIR0ClBLdhy8zzdX2UKGgGR7+mnXNC7btaaAdLAWgIR0ClA//qgRK6dX2UKGgGR7/WMoMKCxu9aAdLBGgIR0ClBD8IZ62OdX2UKGgGR7/Di+cpb2UTaAdLAmgIR0ClBAqODJ2ddX2UKGgGR7/VC6pYLb5/aAdLA2gIR0ClBMYT9KmLdX2UKGgGR7/Cv5gw482aaAdLAmgIR0ClBEmEwnIAdX2UKGgGR7+StFKCg9NfaAdLAWgIR0ClBE26shgWdX2UKGgGR7/GFpPAO8TSaAdLAmgIR0ClBBL433pOdX2UKGgGR7/fpt78ejmCaAdLBmgIR0ClBJDyWiUQdX2UKGgGR7/Ot+TeO4oaaAdLA2gIR0ClBFvkJa7mdX2UKGgGR7/IqKgqVhTgaAdLA2gIR0ClBCFHavicdX2UKGgGR7/RJJ5E+gUUaAdLA2gIR0ClBJ9ld1MedX2UKGgGR7/iZ9Vmz0HyaAdLB2gIR0ClBOV4Pf8/dX2UKGgGR7/BwyZa3ZwoaAdLAmgIR0ClBKgNwzcidX2UKGgGR7/OERJ2+wkgaAdLA2gIR0ClBGlJHy3DdX2UKGgGR7/P5rP+n62waAdLA2gIR0ClBC6S1Vo6dX2UKGgGR7/LsC1Z1V5saAdLA2gIR0ClBPQjdHlPdX2UKGgGR7/HwqiGnGbTaAdLA2gIR0ClBLaYNRWMdX2UKGgGR7/NJjDsMRYjaAdLA2gIR0ClBHfGlyimdX2UKGgGR7/UVNYbKifyaAdLA2gIR0ClBD1MdtEYdX2UKGgGR7/BRbbDdgv2aAdLAmgIR0ClBH/MnqmkdX2UKGgGR7/QvQnhKlHjaAdLA2gIR0ClBQBwdbPhdX2UKGgGR7/SBJ7LMcIaaAdLA2gIR0ClBEj5TIeYdX2UKGgGR7/UGvOhTOxCaAdLBGgIR0ClBMkWhysCdX2UKGgGR7/Teg+QlruZaAdLA2gIR0ClBFbYTTOPdX2UKGgGR7/nFiKBNEgGaAdLB2gIR0ClBKAKv3ajdX2UKGgGR7/KIC2c8TzvaAdLA2gIR0ClBGVzySV4dX2UKGgGR7+cwQDmr8ziaAdLAWgIR0ClBGmlQ/HHdX2UKGgGR7/pBCdBjWkKaAdLCGgIR0ClBOvC/GlzdX2UKGgGR7/RR51Ng0CSaAdLA2gIR0ClBKz5ftx/dX2UKGgGR7+698JD3M6jaAdLAmgIR0ClBHI91U2ldWUu"
56
  },
57
  "ep_success_buffer": {
58
  ":type:": "<class 'collections.deque'>",
 
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 0x79a4e10f4820>",
8
  "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x79a4e10ed480>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
 
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
+ "start_time": 1691505077372613479,
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": "[[-1.8902428 2.3927898 0.8584445 ]\n [ 0.96368456 0.45051548 0.1722909 ]\n [ 0.2670457 0.19426844 -0.15655804]\n [-0.85012966 1.5229547 0.983953 ]]",
34
+ "desired_goal": "[[-1.3970535 1.1627921 0.4129238 ]\n [ 1.1240045 0.42900515 -0.8895806 ]\n [ 0.40549475 0.3258177 -1.117346 ]\n [-0.476341 0.9459833 1.2823477 ]]",
35
+ "observation": "[[-1.8902428 2.3927898 0.8584445 -0.7825618 0.7983607 -0.2410573 ]\n [ 0.96368456 0.45051548 0.1722909 0.72949684 0.8600041 -1.4040041 ]\n [ 0.2670457 0.19426844 -0.15655804 -0.16163966 0.14921804 -1.3841406 ]\n [-0.85012966 1.5229547 0.983953 0.53449386 1.0340693 1.9250941 ]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
 
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": "[[ 0.14130558 -0.0457576 0.15535484]\n [-0.03809611 -0.09082766 0.20729443]\n [-0.13686106 -0.01573191 0.12001962]\n [-0.02427347 0.0606604 0.17791742]]",
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:": "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"
56
  },
57
  "ep_success_buffer": {
58
  ":type:": "<class 'collections.deque'>",
a2c-PandaReachDense-v3/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa373667628ec2736f7408ebb1530024eb65924f76dfe0c3ef15012bd3c54291
3
  size 44734
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88cbb6424e400193eb173e6085536f92eee334e302e7626f242d04b22b325058
3
  size 44734
a2c-PandaReachDense-v3/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10e53e6a8b5ca1893439aeca4cd0acc3c2b7b8760c22e923cf63ac1534858dba
3
  size 46014
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727241e6e49082f82ee0aa63f8f1784f0cec51520188e71dec8d40d66bdac6fd
3
  size 46014
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 0x7d83a7aedc60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7d83a7af0a00>"}, "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": 1691435117619413130, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-4.349957 -0.50133437 -2.4799817 ]\n [ 0.5486673 -0.40149376 0.6618299 ]\n [ 0.5515472 0.4203138 0.66129667]\n [-0.4125532 -0.45368677 0.3317958 ]]", "desired_goal": "[[-1.5457624 0.15444034 -0.8485371 ]\n [ 1.2425882 -0.3560116 1.5531467 ]\n [ 0.74012655 0.10647513 1.4478446 ]\n [-0.60608494 -1.225225 0.0995459 ]]", "observation": "[[-4.349957 -0.50133437 -2.4799817 -0.6413411 -1.6428975 1.5209249 ]\n [ 0.5486673 -0.40149376 0.6618299 1.6701304 -1.5866346 1.117392 ]\n [ 0.5515472 0.4203138 0.66129667 1.6294065 1.5228907 1.0934463 ]\n [-0.4125532 -0.45368677 0.3317958 -0.7524077 -1.6643292 0.6936233 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 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": "[[-0.119279 -0.14456247 0.03911193]\n [-0.13528337 0.05429856 0.19361429]\n [-0.13871914 -0.09893867 0.22887011]\n [ 0.04217126 -0.06041493 0.23179844]]", "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": 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": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "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 0x79a4e10f4820>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x79a4e10ed480>"}, "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": 1691505077372613479, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-1.8902428 2.3927898 0.8584445 ]\n [ 0.96368456 0.45051548 0.1722909 ]\n [ 0.2670457 0.19426844 -0.15655804]\n [-0.85012966 1.5229547 0.983953 ]]", "desired_goal": "[[-1.3970535 1.1627921 0.4129238 ]\n [ 1.1240045 0.42900515 -0.8895806 ]\n [ 0.40549475 0.3258177 -1.117346 ]\n [-0.476341 0.9459833 1.2823477 ]]", "observation": "[[-1.8902428 2.3927898 0.8584445 -0.7825618 0.7983607 -0.2410573 ]\n [ 0.96368456 0.45051548 0.1722909 0.72949684 0.8600041 -1.4040041 ]\n [ 0.2670457 0.19426844 -0.15655804 -0.16163966 0.14921804 -1.3841406 ]\n [-0.85012966 1.5229547 0.983953 0.53449386 1.0340693 1.9250941 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 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": "[[ 0.14130558 -0.0457576 0.15535484]\n [-0.03809611 -0.09082766 0.20729443]\n [-0.13686106 -0.01573191 0.12001962]\n [-0.02427347 0.0606604 0.17791742]]", "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": 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": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.109+-x86_64-with-glibc2.35 # 1 SMP Fri Jun 9 10:57:30 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.0.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "True", "Numpy": "1.22.4", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.25.2"}}
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -15.939823200553656, "std_reward": 2.6233623511271014, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-07T20:39:52.543504"}
 
1
+ {"mean_reward": -0.26090532103553415, "std_reward": 0.1298534430873685, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-08-08T15:23:09.541801"}
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5fa708be9ff4801be5c5fba84bd60abef63f16a7c240bd85511b387a0f56b69
3
- size 2610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bffd4e95d4a147122c3a734b3a4c026ce2ffbdb41d0efdfc7a90b8a831610a04
3
+ size 2623