Hugging Face's logo

wooii
/
a2c-PandaReachDense-v3

Reinforcement Learning
stable-baselines3
PandaReachDense-v3
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Community
wooii commited on
Commit
ea17570
·
1 Parent(s): 9639d66

Initial commit

Browse files
Files changed (9) hide show
  1. README.md +1 -1
  2. a2c-PandaReachDense-v3.zip +2 -2
  3. a2c-PandaReachDense-v3/data +15 -15
  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 +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PandaReachDense-v3
17
  metrics:
18
  - type: mean_reward
19
- value: -27.52 +/- 13.09
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PandaReachDense-v3
17
  metrics:
18
  - type: mean_reward
19
+ value: -0.24 +/- 0.09
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 sha256:0e2a4ca153f2f622e4559119bbab8e6e3849591e317523a48bc09de9cf160c80
3
- size 106571
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c4224eb7b4f23d11d072dd396ead55c95ee1b1f106f64def9f08c663ecb4f36
3
+ size 106592
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 0x7f54c3561630>",
8
  "__abstractmethods__": "frozenset()",
9
- "_abc_impl": "<_abc._abc_data object at 0x7f54c355d240>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
@@ -19,46 +19,46 @@
19
  "weight_decay": 0
20
  }
21
  },
22
- "num_timesteps": 10000,
23
- "_total_timesteps": 10000,
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
- "start_time": 1696421736867093073,
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": "[[ 0.2589643 -0.0221057 0.652166 ]\n [-0.15921013 -1.3092585 0.21185671]\n [ 0.2589643 -0.0221057 0.652166 ]\n [ 0.70084035 -0.97795755 0.918564 ]]",
34
- "desired_goal": "[[ 0.98433214 1.6146616 0.3452868 ]\n [-0.14568402 -1.609984 -0.9978317 ]\n [-1.4651916 -0.20779043 1.3141494 ]\n [ 1.7533973 -1.1917342 0.46428612]]",
35
- "observation": "[[ 0.2589643 -0.0221057 0.652166 0.06186502 0.0061266 0.05902709]\n [-0.15921013 -1.3092585 0.21185671 -2.712192 -1.7855916 -1.8962123 ]\n [ 0.2589643 -0.0221057 0.652166 0.06186502 0.0061266 0.05902709]\n [ 0.70084035 -0.97795755 0.918564 -0.4729254 -0.33503184 -1.41021 ]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
39
- ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.0142992 -0.09848359 0.14661244]\n [ 0.07714345 0.03411168 0.21997455]\n [-0.03119361 0.01739325 0.2882969 ]\n [-0.1091653 0.07057828 0.24533021]]",
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,
49
  "use_sde": false,
50
  "sde_sample_freq": -1,
51
- "_current_progress_remaining": 0.0,
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'>",
59
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
60
  },
61
- "_n_updates": 500,
62
  "n_steps": 5,
63
  "gamma": 0.99,
64
  "gae_lambda": 1.0,
 
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 0x7cd340ca8040>",
8
  "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7cd340ca5680>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
 
19
  "weight_decay": 0
20
  }
21
  },
22
+ "num_timesteps": 599292,
23
+ "_total_timesteps": 1000000,
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
+ "start_time": 1696452280811564068,
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": "[[-0.10360321 -0.37098807 -0.15707605]\n [-0.50537115 -0.37875366 0.31441003]\n [ 0.2120575 -0.00218671 0.39555573]\n [ 0.2120575 -0.00218671 0.39555573]]",
34
+ "desired_goal": "[[-0.4758533 -1.1543751 -0.28287992]\n [-0.39852217 -0.3095969 1.414483 ]\n [-1.5178763 1.5369916 -0.5621574 ]\n [ 1.1931189 -0.6982433 1.3523966 ]]",
35
+ "observation": "[[-0.10360321 -0.37098807 -0.15707605 -1.7872139 -1.6772692 -1.3891549 ]\n [-0.50537115 -0.37875366 0.31441003 -0.8112336 -1.636314 0.87705463]\n [ 0.2120575 -0.00218671 0.39555573 0.43677956 -0.00543719 0.36544266]\n [ 0.2120575 -0.00218671 0.39555573 0.43677956 -0.00543719 0.36544266]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
39
+ ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[ 0.10483778 0.10219989 0.27490133]\n [ 0.05424643 -0.053934 0.16946511]\n [-0.12957864 -0.1464424 0.15637428]\n [ 0.09617842 0.01025058 0.22107412]]",
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,
49
  "use_sde": false,
50
  "sde_sample_freq": -1,
51
+ "_current_progress_remaining": 0.40071999999999997,
52
  "_stats_window_size": 100,
53
  "ep_info_buffer": {
54
  ":type:": "<class 'collections.deque'>",
55
+ ":serialized:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHv761stTUAkuMAWyUSwKMAXSUR0Cfz0JbdJrddX2UKGgGR7/JV6NVBD5TaAdLA2gIR0Cf0TKxs2vTdX2UKGgGR7/AUJv5xiobaAdLAmgIR0Cf0Eq1PWQPdX2UKGgGR7+81AJLM9r5aAdLAmgIR0Cfz2X5nDiwdX2UKGgGR7/QfixVyWAxaAdLA2gIR0Cf0p/MnqmkdX2UKGgGR7+ipeeFtbcHaAdLAWgIR0Cf0rc7yQPqdX2UKGgGR7/RUedTYNAkaAdLA2gIR0Cf0W4dZJTVdX2UKGgGR7+x7kXDWK/EaAdLAmgIR0Cf0HUBnzxxdX2UKGgGR7/HqeK8+RozaAdLA2gIR0Cfz6KWszVMdX2UKGgGR7+36VMVUModaAdLAmgIR0Cf0Jf+CK77dX2UKGgGR7/N72tdRiw0aAdLA2gIR0Cf0aTqSowVdX2UKGgGR7+9v4ubqhUSaAdLAmgIR0Cfz8cGTs6adX2UKGgGR7+ao60Y0l7daAdLAWgIR0Cfz9/Y8Md+dX2UKGgGR7/YfPX05EMLaAdLBWgIR0Cf0yDaoMrmdX2UKGgGR7/CtFKCg9NfaAdLAmgIR0Cf0dflIVdpdX2UKGgGR7+houf29L6DaAdLAWgIR0Cfz/lCTlkpdX2UKGgGR7++1TisGPgfaAdLAmgIR0Cf00ScLBsRdX2UKGgGR7/RtqpLmITHaAdLA2gIR0Cf0gw0fozOdX2UKGgGR7/cQD3dsSCfaAdLB2gIR0Cf0SLPD50sdX2UKGgGR7/XE2YOUdJbaAdLBGgIR0Cf0D3Zf2K3dX2UKGgGR7/LJg9eQdS3aAdLA2gIR0Cf03/gBLf2dX2UKGgGR7/cD3M6ij+KaAdLBGgIR0Cf0ld5prULdX2UKGgGR7/ReRPoFFDwaAdLA2gIR0Cf0HlPrOZ9dX2UKGgGR7/QJAt4A0bcaAdLA2gIR0Cf07PcSGrTdX2UKGgGR7/ZbhWHUMG5aAdLBGgIR0Cf0XBvaURndX2UKGgGR7+HiR4hUzbfaAdLAWgIR0Cf0YEBsANodX2UKGgGR7/MiPhhpg1FaAdLA2gIR0Cf0pOsT37DdX2UKGgGR7/L+98JD3M7aAdLA2gIR0Cf0LVAAyVOdX2UKGgGR7/UguRLbpNcaAdLA2gIR0Cf0+73wkPddX2UKGgGR7/EdgfEGZ/kaAdLAmgIR0Cf0rTHsC1adX2UKGgGR7/OhJRO1v2oaAdLA2gIR0Cf0buUUwi8dX2UKGgGR7+zY5DJEH+qaAdLAmgIR0Cf0NaEzwc6dX2UKGgGR7+33pOerdWRaAdLAmgIR0Cf1BCUX531dX2UKGgGR7+h1xKg7HQyaAdLAWgIR0Cf0Oel9BrvdX2UKGgGR7+34N7SiM5waAdLAmgIR0Cf0tgQHzH0dX2UKGgGR7/TxPO6d1+zaAdLA2gIR0Cf0fXD3ueCdX2UKGgGR7/DsE7nxJ/YaAdLAmgIR0Cf0RD2JzkqdX2UKGgGR7/KyeI2wV0taAdLA2gIR0Cf1EpiZv1ldX2UKGgGR7/Lw6ySmqHXaAdLA2gIR0Cf0xLpiZv2dX2UKGgGR7+5BlcyFfzCaAdLAmgIR0Cf0hnscABDdX2UKGgGR7/PVtGd7OVxaAdLA2gIR0Cf0UlsguAadX2UKGgGR7/NW8RL9MsZaAdLA2gIR0Cf1ILWqcVhdX2UKGgGR7+5wDNhVlwtaAdLAmgIR0Cf0zoOQQtjdX2UKGgGR7+vkiliz9jxaAdLAmgIR0Cf0kD50r9VdX2UKGgGR7/KpR4yGi5/aAdLA2gIR0Cf0YNo8IRidX2UKGgGR7/QXnQpnYg8aAdLA2gIR0Cf1L1RLsa9dX2UKGgGR7/QgOz6ab4KaAdLA2gIR0Cf03SZjQRgdX2UKGgGR7/SOkLx7RfGaAdLA2gIR0Cf0nuJDVpcdX2UKGgGR7/FlGPPszEaaAdLAmgIR0Cf1OPS2H+IdX2UKGgGR7/EeeWfK6nSaAdLA2gIR0Cf0buX/o7ndX2UKGgGR7/Ob0e2d/ayaAdLA2gIR0Cf07QE6kqMdX2UKGgGR7/OW1twaR6oaAdLA2gIR0Cf0rsQumJndX2UKGgGR7+c9SuQp4KQaAdLAWgIR0Cf0dXyRSxadX2UKGgGR7+nqxC6Ymb9aAdLAWgIR0Cf08eoUBXCdX2UKGgGR7/U5SFXaJyiaAdLA2gIR0Cf1SJ/5LyudX2UKGgGR7+6hufmLcbjaAdLAmgIR0Cf0+lcQiA2dX2UKGgGR7/OvWYnfEXMaAdLA2gIR0Cf0vDUmUnpdX2UKGgGR7/Q5TqB3A2yaAdLBGgIR0Cf0hxREWqMdX2UKGgGR7/GstkFwDNhaAdLA2gIR0Cf1CLTQVsUdX2UKGgGR7/PzFMqSX+maAdLA2gIR0Cf0ymFrVOLdX2UKGgGR7+7pIMBp5/taAdLAmgIR0Cf0kUADJU6dX2UKGgGR7/eYKYzBRAKaAdLBWgIR0Cf1X6TGHYZdX2UKGgGR7+laKUFB6a9aAdLAWgIR0Cf1DWac7QtdX2UKGgGR7/CCSzPa+N+aAdLAmgIR0Cf0040/GEPdX2UKGgGR7/CfOlfqoqDaAdLAmgIR0Cf1Fhg3LmqdX2UKGgGR7/RE5yU9pyqaAdLA2gIR0Cf0nmF8G9pdX2UKGgGR7/cMrmQr+YMaAdLBGgIR0Cf1c2pyZKGdX2UKGgGR7+2mvW6K+BZaAdLAmgIR0Cf1IUB4lhPdX2UKGgGR7/Ig1WKdhAoaAdLA2gIR0Cf04v5P/JedX2UKGgGR7/MyRjjJdSmaAdLA2gIR0Cf0rcZtNzsdX2UKGgGR7+oI2OyVv/BaAdLAWgIR0Cf0scD8tPIdX2UKGgGR7/Tgntv4ubraAdLA2gIR0Cf1gBYmsvJdX2UKGgGR7/H0K7ZnL7oaAdLA2gIR0Cf1LhAWznidX2UKGgGR7/RUwi7kGRnaAdLA2gIR0Cf08AX2ugZdX2UKGgGR7+9xDLKV6eHaAdLAmgIR0Cf0vPacqe9dX2UKGgGR7+7NzKcNH6NaAdLAmgIR0Cf1OPvKEFodX2UKGgGR7/PErGza9K3aAdLA2gIR0Cf1j7r9l3AdX2UKGgGR7/VB55Z8rqdaAdLBGgIR0Cf1AwN9YwJdX2UKGgGR7/LfuTibUgCaAdLA2gIR0Cf0ydSl3yJdX2UKGgGR7/aPi1iONo8aAdLBGgIR0Cf1oqbBoEkdX2UKGgGR7/YkoF3Y+SsaAdLBWgIR0Cf1UIZ62ORdX2UKGgGR7/RdhRZU1htaAdLA2gIR0Cf1ElWwNb1dX2UKGgGR7/Q0ALiMo+faAdLA2gIR0Cf02SXt0FKdX2UKGgGR7+QTZg5R0lraAdLAWgIR0Cf1p9KmKqGdX2UKGgGR7+64smOU+s6aAdLAmgIR0Cf1WZGrjo7dX2UKGgGR7/R9FnZkCmuaAdLA2gIR0Cf1H2tMfzSdX2UKGgGR7/Pb9If8uSPaAdLA2gIR0Cf05tGNJe3dX2UKGgGR7/N5BTn7pFDaAdLA2gIR0Cf1t9ugpSadX2UKGgGR7/EESuhbnoxaAdLAmgIR0Cf1ZbcGkeqdX2UKGgGR7++loDgZTAGaAdLAmgIR0Cf1K/WDpTudX2UKGgGR7+/jvNNahYeaAdLAmgIR0Cf08uCwr1/dX2UKGgGR7+mZmZmZmZmaAdLAWgIR0Cf090Cih38dX2UKGgGR7/McuJ1q33IaAdLA2gIR0Cf1xfWMCLddX2UKGgGR7/RqXF98Z1naAdLA2gIR0Cf1c8gZCOWdX2UKGgGR7/HkELYwqRVaAdLA2gIR0Cf1Oa6jFhodX2UKGgGR7+7fwZwXIluaAdLAmgIR0Cf1AKVpsXSdX2UKGgGR7/P/m1YyO7yaAdLA2gIR0Cf11dt2s7udX2UKGgGR7/QYixFAmiQaAdLA2gIR0Cf1hA8SwnqdX2UKGgGR7/MvFm4AjptaAdLA2gIR0Cf1SsNDtw8dX2UKGgGR7/UN7jT8YQ8aAdLA2gIR0Cf1EZlnRLLdWUu"
56
  },
57
  "ep_success_buffer": {
58
  ":type:": "<class 'collections.deque'>",
59
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
60
  },
61
+ "_n_updates": 29964,
62
  "n_steps": 5,
63
  "gamma": 0.99,
64
  "gae_lambda": 1.0,
a2c-PandaReachDense-v3/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:351f9252ed3d624c27ee93b352bb7a4f06410faf1c106970dcf89ec3706c556e
3
  size 44606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fba15e1841b3289e2b1158ab97803ce7c59076ba0fdfb9fcfb2f9a26ed2b2eae
3
  size 44606
a2c-PandaReachDense-v3/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2e47680f931abc3a8f0674984e59237a6d8441f8396675b10ac72ffef31d20d9
3
  size 45886
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1bb417e45965d6f98ea929a4c28f922cb2a0d613c644540bc968a0369d84899
3
  size 45886
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 0x7f54c3561630>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f54c355d240>"}, "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": 10000, "_total_timesteps": 10000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696421736867093073, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.2589643 -0.0221057 0.652166 ]\n [-0.15921013 -1.3092585 0.21185671]\n [ 0.2589643 -0.0221057 0.652166 ]\n [ 0.70084035 -0.97795755 0.918564 ]]", "desired_goal": "[[ 0.98433214 1.6146616 0.3452868 ]\n [-0.14568402 -1.609984 -0.9978317 ]\n [-1.4651916 -0.20779043 1.3141494 ]\n [ 1.7533973 -1.1917342 0.46428612]]", "observation": "[[ 0.2589643 -0.0221057 0.652166 0.06186502 0.0061266 0.05902709]\n [-0.15921013 -1.3092585 0.21185671 -2.712192 -1.7855916 -1.8962123 ]\n [ 0.2589643 -0.0221057 0.652166 0.06186502 0.0061266 0.05902709]\n [ 0.70084035 -0.97795755 0.918564 -0.4729254 -0.33503184 -1.41021 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.0142992 -0.09848359 0.14661244]\n [ 0.07714345 0.03411168 0.21997455]\n [-0.03119361 0.01739325 0.2882969 ]\n [-0.1091653 0.07057828 0.24533021]]", "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:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHwCvWzIFNcnqMAWyUSzKMAXSUR0BBsX49HMEBdX2UKGgGR8AqVwQ176YWaAdLMmgIR0BCIr1VYISldX2UKGgGR8AFUgwGnn+yaAdLFmgIR0BB6TPrv9cbdX2UKGgGR8Aos1cdHUc5aAdLMmgIR0BCT+wTufEodX2UKGgGR8ArqWIoE0SAaAdLMmgIR0BCF3hGYrrgdX2UKGgGR8AkcGh24d6taAdLMmgIR0BCkZvDP4VRdX2UKGgGR8Ao1mQr+YMOaAdLMmgIR0BCWeRxLkCFdX2UKGgGR8Avp8MNMGoraAdLMmgIR0BC1FOGj9GadX2UKGgGR8AyIpPykKu0aAdLMmgIR0BCm655JK8MdX2UKGgGR8Ac2Gyon8baaAdLMmgIR0BDFZq20AtGdX2UKGgGR8AuFvfCQ9zPaAdLMmgIR0BC3Ur08NhFdX2UKGgGR8AqUuYhMajvaAdLMmgIR0BDViIDYAbRdX2UKGgGR8AyPuh9LHuJaAdLMmgIR0BDHY1He7+UdX2UKGgGR8ApE/etSydGaAdLMmgIR0BDl9AxBVuKdX2UKGgGR8AklVKf4AS4aAdLMmgIR0BDYDWsijcmdX2UKGgGR8Aa95hScbzcaAdLKWgIR0BDwHCGetjkdX2UKGgGR8AmFZUT+NtJaAdLMmgIR0BDn9xQzk6tdX2UKGgGR8AjpnOB19v1aAdLMmgIR0BEGZ00WM0hdX2UKGgGR8AlFfek56t1aAdLMmgIR0BD4kuYhMakdX2UKGgGR8AnPSaVlf7aaAdLMmgIR0BEOBm5DqnndX2UKGgGR7/LX18LKFIvaAdLA2gIR0BEPMVUMoc8dX2UKGgGR8AtmPOpsGgSaAdLMmgIR0BEDCNjslcAdX2UKGgGR7/wVj3Ehq0uaAdLCmgIR0BEHmsFMZgpdX2UKGgGR8Ag1mOlwcYJaAdLMmgIR0BEfkvkBCD3dX2UKGgGR8AgXO5avA45aAdLMmgIR0BERBDgIhQndX2UKGgGR8AnTi3ocJdCaAdLMmgIR0BEjgskIHC5dX2UKGgGR8AqhErGza9LaAdLMmgIR0BEb1jZtelbdX2UKGgGR8AubGrCFbmmaAdLMmgIR0BEzxZ2ZApsdX2UKGgGR8Aj1OpsGgSOaAdLMmgIR0BEldznzQNTdX2UKGgGR8AlDhYvFm4BaAdLMmgIR0BE5Hu7YkE+dX2UKGgGR8AkabjLjghsaAdLMmgIR0BExRjz7MxHdX2UKGgGR8AlJXXiBGx2aAdLMmgIR0BFJQkxASnMdX2UKGgGR8Ac6HnEETxoaAdLMmgIR0BE6yRKYiPidX2UKGgGR7/37tzCDVYqaAdLC2gIR0BE15DJEH+qdX2UKGgGR7/z2RzRx95RaAdLCmgIR0BE+yFfzBhydX2UKGgGR8AlQBOHnEEUaAdLMmgIR0BFNesHSncddX2UKGgGR7+RxLkCFK02aAdLAWgIR0BFN0C7sfJWdX2UKGgGR8AXb0XgtOEeaAdLLmgIR0BFbnivPkaNdX2UKGgGR8AjlU3GXHBDaAdLMmgIR0BFKWLYPGyYdX2UKGgGR8AxAxiXpnpTaAdLMmgIR0BFTQmmce8xdX2UKGgGR7/iwY1pCa7VaAdLBWgIR0BFVMvqTr3TdX2UKGgGR8AivDv3JxNqaAdLMmgIR0BFiJQDV6NVdX2UKGgGR8AwWj4HoouxaAdLMmgIR0BFv+6Ae7tidX2UKGgGR8AqToGpuMuOaAdLMmgIR0BFeTF+/gzhdX2UKGgGR8AhVjU/fO2RaAdLMmgIR0BFphE0BOpLdX2UKGgGR7/t5IpYs/Y8aAdLCWgIR0BFiJSJj2BbdX2UKGgGR8AlKCf6GgzyaAdLMmgIR0BF3V4oqkM1dX2UKGgGR8Av3IZqEeySaAdLMmgIR0BGFyNn5BTodX2UKGgGR8AwIq2jO9nLaAdLMmgIR0BF/oybhFVldX2UKGgGR8AoaQ9RrJr+aAdLMmgIR0BF4QHJLdvbdX2UKGgGR8ALAOUdJaq0aAdLGmgIR0BGQ5TZQHiWdX2UKGgGR8AhNyqdYnv2aAdLL2gIR0BGLtoi9qUNdX2UKGgGR8Ak9OmixmkFaAdLMmgIR0BGTu7xusLfdX2UKGgGR8ArNF8XvYvnaAdLMmgIR0BGMXKji4rjdX2UKGgGR8AjqAd4mkWRaAdLMmgIR0BGlHnEETxodX2UKGgGR8Ar2rbxmTTwaAdLMmgIR0BGgUk4WDYidX2UKGgGR8Ayn+3Ytg8baAdLMmgIR0BGod4eLehxdX2UKGgGR8AiBdKNAC4jaAdLMmgIR0BGhGDL8rI6dX2UKGgGR8AhLGqgh8pkaAdLMmgIR0BG5tc4YJmedX2UKGgGR7/hfIsAeaKDaAdLBmgIR0BGjohQm/nGdX2UKGgGR8An8KkVN5+paAdLMmgIR0BG03xnWattdX2UKGgGR8AkTiEQGwA3aAdLMmgIR0BG+BtcfNiZdX2UKGgGR8A3qhje9Ba+aAdLMmgIR0BHPNjkMkQgdX2UKGgGR8AquNI9TxXoaAdLMmgIR0BG5SzollbvdX2UKGgGR7/LaPjn3cpLaAdLA2gIR0BHQwNsnAqNdX2UKGgGR8AqGX531SOzaAdLMmgIR0BHKhTn7pFDdX2UKGgGR8AVV7u2JBPbaAdLJmgIR0BHa2KEWZZ0dX2UKGgGR8AtfmnwXqJNaAdLMmgIR0BHT7LlmvnsdX2UKGgGR7/HOxjawljWaAdLA2gIR0BHVhF/hESedX2UKGgGR8AkOez2OAAiaAdLMmgIR0BHPT4UN8VpdX2UKGgGR8Ad1cY64lQeaAdLMmgIR0BHmt0NjLB9dX2UKGgGR7/1IJAt4A0baAdLDGgIR0BHabDVH4GmdX2UKGgGR8At+M2FWXC1aAdLMmgIR0BHvXNke6qbdX2UKGgGR8ApIB06o2n9aAdLMmgIR0BHjfRmbsnidX2UKGgGR8AzqHmRvFWGaAdLMmgIR0BH617x/d6+dX2UKGgGR8ArlHmRvFWGaAdLMmgIR0BHumpuMuOCdX2UKGgGR8ABn114gRseaAdLFmgIR0BH4UYCQtBfdX2UKGgGR7/hSxRl6JIlaAdLBmgIR0BHw1JlJ6IFdX2UKGgGR7/72kJrtVrAaAdLD2gIR0BHpcqOLiuMdX2UKGgGR7/BOLR8c+7laAdLAmgIR0BHxllbu+h5dX2UKGgGR8Ai1gVGkN4JaAdLMmgIR0BIPoZQ53kgdX2UKGgGR8AmlTcZccENaAdLMmgIR0BINivgWJrMdX2UKGgGR8AwBOXVsk6caAdLMmgIR0BH+v2wmmcfdX2UKGgGR8AnqnUDuBtlaAdLMmgIR0BIG9SVGCqZdX2UKGgGR7/pOQQtjCpFaAdLB2gIR0BIJfR/mT1TdX2UKGgGR8AtQapgkTpQaAdLMmgIR0BIkOTRplBhdX2UKGgGR7/9wRXfZVXFaAdLC2gIR0BIowpnYg7pdX2UKGgGR8A3j5Jbt7a7aAdLMmgIR0BIiDj7yhBadX2UKGgGR8ArlPomois5aAdLMmgIR0BITUF0PpY+dX2UKGgGR7/To5xR2r4naAdLBGgIR0BIjnQY1pCbdX2UKGgGR8Ak3XJ5mh/RaAdLMmgIR0BIeE0BOpKjdX2UKGgGR8A3erilzltCaAdLMmgIR0BI9i2c8TzvdX2UKGgGR8Appt8eCCjDaAdLMmgIR0BIoBV+7UXpdX2UKGgGR8AwbokRjBl+aAdLMmgIR0BI4iiRGMGYdX2UKGgGR7/xqYVqN6w/aAdLC2gIR0BJCYh2W6bwdX2UKGgGR8AjlQtSQ5mzaAdLMmgIR0BIzPeHi3ocdX2UKGgGR8AqWmVqveP8aAdLMmgIR0BJAIre67NCdX2UKGgGR8Ar8wSJ0nw5aAdLMmgIR0BJRO6NEPUbdX2UKGgGR8AzDHuqm0mdaAdLMmgIR0BJcqCpWFN+dX2UKGgGR8AyFBltj0+UaAdLMmgIR0BJNlJQLux9dWUu"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 500, "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-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "False", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "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 0x7cd340ca8040>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7cd340ca5680>"}, "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": 599292, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1696452280811564068, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.10360321 -0.37098807 -0.15707605]\n [-0.50537115 -0.37875366 0.31441003]\n [ 0.2120575 -0.00218671 0.39555573]\n [ 0.2120575 -0.00218671 0.39555573]]", "desired_goal": "[[-0.4758533 -1.1543751 -0.28287992]\n [-0.39852217 -0.3095969 1.414483 ]\n [-1.5178763 1.5369916 -0.5621574 ]\n [ 1.1931189 -0.6982433 1.3523966 ]]", "observation": "[[-0.10360321 -0.37098807 -0.15707605 -1.7872139 -1.6772692 -1.3891549 ]\n [-0.50537115 -0.37875366 0.31441003 -0.8112336 -1.636314 0.87705463]\n [ 0.2120575 -0.00218671 0.39555573 0.43677956 -0.00543719 0.36544266]\n [ 0.2120575 -0.00218671 0.39555573 0.43677956 -0.00543719 0.36544266]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAA6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+6nIdPRlsGqxDI0o+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAAMLXWPS1O0T3ev4w+gDFePeXpXL1DiC0+Q7AEvv/0Fb6UICA+MfnEPQ3yJzxBYWI+lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWYAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACUaA5LBEsGhpRoEnSUUpR1Lg==", "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": "[[ 0.10483778 0.10219989 0.27490133]\n [ 0.05424643 -0.053934 0.16946511]\n [-0.12957864 -0.1464424 0.15637428]\n [ 0.09617842 0.01025058 0.22107412]]", "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": 0.40071999999999997, "_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": 29964, "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:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9G8AaNuLrHhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-5.15.120+-x86_64-with-glibc2.35 # 1 SMP Wed Aug 30 11:19:59 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu118", "GPU Enabled": "False", "Numpy": "1.23.5", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "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": -27.5208449780941, "std_reward": 13.091078430705233, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-04T12:17:10.435056"}
 
1
+ {"mean_reward": -0.23780038952827454, "std_reward": 0.08516693335115273, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-10-04T21:18:45.187202"}
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d041b2a95299d1b2f9b7ad3138af83158b714d3613386bb947a52a2453532ced
3
  size 2623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34eae6ed424833905c575605cac9cf4ec8a8d001b3adf135c360a418fbf6208f
3
  size 2623