Kurokabe commited on
Commit
5908772
1 Parent(s): efeb794

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PandaPushDense-v2
17
  metrics:
18
  - type: mean_reward
19
- value: -8.31 +/- 3.41
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PandaPushDense-v2
17
  metrics:
18
  - type: mean_reward
19
+ value: -7.32 +/- 2.06
20
  name: mean_reward
21
  verified: false
22
  ---
a2c-PandaPushDense-v2.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ccaf19d5820c38b498a339e7be1543897285d4be5915f0947fef750c07db70f
3
- size 117344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f951d07d4a41c8a5fd9f09cdb3938ee040b55c936dc57101f7e586d5f65a12
3
+ size 122466
a2c-PandaPushDense-v2/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 0x7f5a28c4a5f0>",
8
  "__abstractmethods__": "frozenset()",
9
- "_abc_impl": "<_abc._abc_data object at 0x7f5a28c50580>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
@@ -41,12 +41,12 @@
41
  "_np_random": null
42
  },
43
  "n_envs": 4,
44
- "num_timesteps": 20,
45
- "_total_timesteps": 10,
46
  "_num_timesteps_at_start": 0,
47
  "seed": null,
48
  "action_noise": null,
49
- "start_time": 1676810545216914887,
50
  "learning_rate": 0.0007,
51
  "tensorboard_log": null,
52
  "lr_schedule": {
@@ -55,35 +55,35 @@
55
  },
56
  "_last_obs": {
57
  ":type:": "<class 'collections.OrderedDict'>",
58
- ":serialized:": "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",
59
- "achieved_goal": "[[ 1.4375114e+00 3.7055409e-01 -8.3448819e-04]\n [ 4.0368223e-01 1.1364377e+00 -8.3448819e-04]\n [-1.1124331e+00 -1.5997032e+00 -8.3448819e-04]\n [-7.2877222e-01 9.2787325e-02 -8.3448819e-04]]",
60
- "desired_goal": "[[ 1.6787918e+00 -1.7057517e+00 4.0767707e-05]\n [-2.5586367e-01 4.0557161e-01 4.0767707e-05]\n [-9.3583465e-01 4.5362788e-01 4.0767707e-05]\n [-4.8710012e-01 8.4655762e-01 4.0767707e-05]]",
61
- "observation": "[[-2.2828999e+00 1.8026731e+00 -6.9599640e-01 -2.5590426e-01\n -3.7827924e-01 -4.7194764e-01 1.4375114e+00 3.7055409e-01\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695971e-06\n 2.5336739e-02 -7.8686383e-03]\n [-1.8001274e+00 1.2900239e+00 1.7174590e+00 -6.2497097e-01\n 1.1568509e+00 1.4558060e-01 4.0368223e-01 1.1364377e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695967e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 6.1482060e-01 -1.0674846e-01 -2.2677412e+00 -1.1223067e+00\n 1.6859711e+00 -1.5176313e+00 -1.1124331e+00 -1.5997032e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0696285e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 8.1928092e-01 -2.6075025e+00 -1.4119338e+00 1.7270075e-01\n -7.5215530e-01 3.9653251e-01 -7.2877222e-01 9.2787325e-02\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695976e-06\n 2.5336739e-02 -7.8686383e-03]]"
62
  },
63
  "_last_episode_starts": {
64
  ":type:": "<class 'numpy.ndarray'>",
65
- ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
66
  },
67
  "_last_original_obs": {
68
  ":type:": "<class 'collections.OrderedDict'>",
69
- ":serialized:": "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",
70
- "achieved_goal": "[[ 0.11815833 0.07831377 0.02 ]\n [ 0.02371145 0.13088465 0.02 ]\n [-0.11479533 -0.05692631 0.02 ]\n [-0.07974548 0.05924763 0.02 ]]",
71
- "desired_goal": "[[ 0.09253775 -0.09521101 0.02 ]\n [-0.04829011 0.05066176 0.02 ]\n [-0.0977867 0.053982 0.02 ]\n [-0.06512232 0.08112978 0.02 ]]",
72
- "observation": "[[ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 1.18158326e-01 7.83137679e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 2.37114523e-02 1.30884647e-01\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 -1.14795335e-01 -5.69263138e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 -7.97454789e-02 5.92476279e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]]"
73
  },
74
  "_episode_num": 0,
75
  "use_sde": false,
76
  "sde_sample_freq": -1,
77
- "_current_progress_remaining": -1.0,
78
  "ep_info_buffer": {
79
  ":type:": "<class 'collections.deque'>",
80
- ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
81
  },
82
  "ep_success_buffer": {
83
  ":type:": "<class 'collections.deque'>",
84
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
85
  },
86
- "_n_updates": 1,
87
  "n_steps": 5,
88
  "gamma": 0.99,
89
  "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 0x7f3b8ba0a5f0>",
8
  "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7f3b8b9ff840>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
 
41
  "_np_random": null
42
  },
43
  "n_envs": 4,
44
+ "num_timesteps": 2000000,
45
+ "_total_timesteps": 2000000,
46
  "_num_timesteps_at_start": 0,
47
  "seed": null,
48
  "action_noise": null,
49
+ "start_time": 1676811067962506994,
50
  "learning_rate": 0.0007,
51
  "tensorboard_log": null,
52
  "lr_schedule": {
 
55
  },
56
  "_last_obs": {
57
  ":type:": "<class 'collections.OrderedDict'>",
58
+ ":serialized:": "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",
59
+ "achieved_goal": "[[ 1.211954 -1.6102103 0.05274928]\n [ 0.8002745 0.45536152 0.05274928]\n [-1.5007739 -1.5373871 0.05274928]\n [-1.1573349 1.5223535 0.05274928]]",
60
+ "desired_goal": "[[-5.2933162e-01 1.6323195e+00 9.3391135e-09]\n [ 2.5219077e-01 -4.3195447e-01 9.3391135e-09]\n [-1.0771869e+00 1.7302885e+00 9.3391135e-09]\n [ 6.8596333e-01 -1.7261465e+00 9.3391135e-09]]",
61
+ "observation": "[[ 0.42512155 -0.9296893 -0.46783745 0.2155716 -0.23401603 -0.05699742\n 1.211954 -1.6102103 0.05274928 0.00622481 -0.0085733 -0.00681216\n 0.01028107 0.01855404 0.0244071 -0.00637061 -0.0089864 0.00179365]\n [ 0.42512155 -0.9296893 -0.46783745 0.2155716 -0.23401603 -0.05699742\n 0.8002745 0.45536152 0.05274928 0.00622481 -0.0085733 -0.00681216\n 0.01028107 0.01855404 0.0244071 -0.00637061 -0.0089864 0.00179365]\n [ 0.42512155 -0.9296893 -0.46783745 0.2155716 -0.23401603 -0.05699742\n -1.5007739 -1.5373871 0.05274928 0.00622481 -0.0085733 -0.00681216\n 0.01028107 0.01855404 0.0244071 -0.00637061 -0.0089864 0.00179365]\n [ 0.42512155 -0.9296893 -0.46783745 0.2155716 -0.23401603 -0.05699742\n -1.1573349 1.5223535 0.05274928 0.00622481 -0.0085733 -0.00681216\n 0.01028107 0.01855404 0.0244071 -0.00637061 -0.0089864 0.00179365]]"
62
  },
63
  "_last_episode_starts": {
64
  ":type:": "<class 'numpy.ndarray'>",
65
+ ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
66
  },
67
  "_last_original_obs": {
68
  ":type:": "<class 'collections.OrderedDict'>",
69
+ ":serialized:": "gAWVewIAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAAfR2PvTb8lT0K16M8qvYQPfKz/70K16M8EfxJvfWMor0K16M8cqXuvKSC4r0K16M8lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAAxf/svcsxtTsK16M8zfvDPTcOZrwK16M8DvdDvEaBlLsK16M88X59ParAODwK16M8lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWIAEAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAB9HY+9NvyVPQrXozwAAAAAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAACq9hA98rP/vQrXozwAAAAAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAAAR/Em99YyivQrXozwAAAAAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAADqch09GWwarEMjSj4AAAAAAAAAgAAAAABype68pILivQrXozwAAAAAAAAAgAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAACUaA5LBEsShpRoEnSUUpR1Lg==",
70
+ "achieved_goal": "[[-0.06988046 0.07323496 0.02 ]\n [ 0.03539149 -0.12485494 0.02 ]\n [-0.04931265 -0.07937042 0.02 ]\n [-0.02913162 -0.11060074 0.02 ]]",
71
+ "desired_goal": "[[-0.11572222 0.00552962 0.02 ]\n [ 0.09569512 -0.01404148 0.02 ]\n [-0.01196076 -0.00453201 0.02 ]\n [ 0.06188864 0.0112764 0.02 ]]",
72
+ "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 -6.9880463e-02 7.3234960e-02\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 3.5391487e-02 -1.2485494e-01\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 -4.9312655e-02 -7.9370417e-02\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 -2.9131625e-02 -1.1060074e-01\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00]]"
73
  },
74
  "_episode_num": 0,
75
  "use_sde": false,
76
  "sde_sample_freq": -1,
77
+ "_current_progress_remaining": 0.0,
78
  "ep_info_buffer": {
79
  ":type:": "<class 'collections.deque'>",
80
+ ":serialized:": "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"
81
  },
82
  "ep_success_buffer": {
83
  ":type:": "<class 'collections.deque'>",
84
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
85
  },
86
+ "_n_updates": 100000,
87
  "n_steps": 5,
88
  "gamma": 0.99,
89
  "gae_lambda": 1.0,
a2c-PandaPushDense-v2/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa618d0eb3f327a6e3b54c997846dcb1bafd74a65b7739588c9f169ef40566e9
3
  size 50878
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75c59e4d154f4f54de71f0e91958285888d826988d9a5e7f2cea34b8e9c199e6
3
  size 50878
a2c-PandaPushDense-v2/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b1610509fd05d7456615282f102202827c2b03d0058e6c7bca6871deb74c9df
3
  size 52158
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e67ccb4cd9880cb3d317a22b3f997abadaa9343e237147e7dcbca834903661ee
3
  size 52158
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 0x7f5a28c4a5f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f5a28c50580>"}, "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}}, "observation_space": {":type:": "<class 'gym.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10. -10. -10. -10. -10. -10. -10. -10. -10.\n -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10.], (18,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 20, "_total_timesteps": 10, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676810545216914887, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 1.4375114e+00 3.7055409e-01 -8.3448819e-04]\n [ 4.0368223e-01 1.1364377e+00 -8.3448819e-04]\n [-1.1124331e+00 -1.5997032e+00 -8.3448819e-04]\n [-7.2877222e-01 9.2787325e-02 -8.3448819e-04]]", "desired_goal": "[[ 1.6787918e+00 -1.7057517e+00 4.0767707e-05]\n [-2.5586367e-01 4.0557161e-01 4.0767707e-05]\n [-9.3583465e-01 4.5362788e-01 4.0767707e-05]\n [-4.8710012e-01 8.4655762e-01 4.0767707e-05]]", "observation": "[[-2.2828999e+00 1.8026731e+00 -6.9599640e-01 -2.5590426e-01\n -3.7827924e-01 -4.7194764e-01 1.4375114e+00 3.7055409e-01\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695971e-06\n 2.5336739e-02 -7.8686383e-03]\n [-1.8001274e+00 1.2900239e+00 1.7174590e+00 -6.2497097e-01\n 1.1568509e+00 1.4558060e-01 4.0368223e-01 1.1364377e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695967e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 6.1482060e-01 -1.0674846e-01 -2.2677412e+00 -1.1223067e+00\n 1.6859711e+00 -1.5176313e+00 -1.1124331e+00 -1.5997032e+00\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0696285e-06\n 2.5336739e-02 -7.8686383e-03]\n [ 8.1928092e-01 -2.6075025e+00 -1.4119338e+00 1.7270075e-01\n -7.5215530e-01 3.9653251e-01 -7.2877222e-01 9.2787325e-02\n -8.3448819e-04 3.6614048e-04 -3.5740482e-03 -4.7284765e-03\n 4.5321445e-04 8.9328521e-04 5.0732616e-04 -5.0695976e-06\n 2.5336739e-02 -7.8686383e-03]]"}, "_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": "[[ 0.11815833 0.07831377 0.02 ]\n [ 0.02371145 0.13088465 0.02 ]\n [-0.11479533 -0.05692631 0.02 ]\n [-0.07974548 0.05924763 0.02 ]]", "desired_goal": "[[ 0.09253775 -0.09521101 0.02 ]\n [-0.04829011 0.05066176 0.02 ]\n [-0.0977867 0.053982 0.02 ]\n [-0.06512232 0.08112978 0.02 ]]", "observation": "[[ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 1.18158326e-01 7.83137679e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 2.37114523e-02 1.30884647e-01\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 -1.14795335e-01 -5.69263138e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]\n [ 3.84396687e-02 -2.19447225e-12 1.97400138e-01 0.00000000e+00\n -0.00000000e+00 0.00000000e+00 -7.97454789e-02 5.92476279e-02\n 1.99999996e-02 0.00000000e+00 -0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00 0.00000000e+00 0.00000000e+00\n 0.00000000e+00 0.00000000e+00]]"}, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": -1.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 1, "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, "system_info": {"OS": "Linux-5.4.0-137-generic-x86_64-with-glibc2.27 # 154-Ubuntu SMP Thu Jan 5 17:03:22 UTC 2023", "Python": "3.10.8", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
 
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 0x7f3b8ba0a5f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7f3b8b9ff840>"}, "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}}, "observation_space": {":type:": "<class 'gym.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('desired_goal', Box([-10. -10. -10.], [10. 10. 10.], (3,), float32)), ('observation', Box([-10. -10. -10. -10. -10. -10. -10. -10. -10. -10. -10. -10. -10. -10.\n -10. -10. -10. -10.], [10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10. 10.], (18,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1676811067962506994, "learning_rate": 0.0007, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 1.211954 -1.6102103 0.05274928]\n [ 0.8002745 0.45536152 0.05274928]\n [-1.5007739 -1.5373871 0.05274928]\n [-1.1573349 1.5223535 0.05274928]]", "desired_goal": "[[-5.2933162e-01 1.6323195e+00 9.3391135e-09]\n [ 2.5219077e-01 -4.3195447e-01 9.3391135e-09]\n [-1.0771869e+00 1.7302885e+00 9.3391135e-09]\n [ 6.8596333e-01 -1.7261465e+00 9.3391135e-09]]", "observation": "[[ 0.42512155 -0.9296893 -0.46783745 0.2155716 -0.23401603 -0.05699742\n 1.211954 -1.6102103 0.05274928 0.00622481 -0.0085733 -0.00681216\n 0.01028107 0.01855404 0.0244071 -0.00637061 -0.0089864 0.00179365]\n [ 0.42512155 -0.9296893 -0.46783745 0.2155716 -0.23401603 -0.05699742\n 0.8002745 0.45536152 0.05274928 0.00622481 -0.0085733 -0.00681216\n 0.01028107 0.01855404 0.0244071 -0.00637061 -0.0089864 0.00179365]\n [ 0.42512155 -0.9296893 -0.46783745 0.2155716 -0.23401603 -0.05699742\n -1.5007739 -1.5373871 0.05274928 0.00622481 -0.0085733 -0.00681216\n 0.01028107 0.01855404 0.0244071 -0.00637061 -0.0089864 0.00179365]\n [ 0.42512155 -0.9296893 -0.46783745 0.2155716 -0.23401603 -0.05699742\n -1.1573349 1.5223535 0.05274928 0.00622481 -0.0085733 -0.00681216\n 0.01028107 0.01855404 0.0244071 -0.00637061 -0.0089864 0.00179365]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.06988046 0.07323496 0.02 ]\n [ 0.03539149 -0.12485494 0.02 ]\n [-0.04931265 -0.07937042 0.02 ]\n [-0.02913162 -0.11060074 0.02 ]]", "desired_goal": "[[-0.11572222 0.00552962 0.02 ]\n [ 0.09569512 -0.01404148 0.02 ]\n [-0.01196076 -0.00453201 0.02 ]\n [ 0.06188864 0.0112764 0.02 ]]", "observation": "[[ 3.8439669e-02 -2.1944723e-12 1.9740014e-01 0.0000000e+00\n -0.0000000e+00 0.0000000e+00 -6.9880463e-02 7.3234960e-02\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 3.5391487e-02 -1.2485494e-01\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 -4.9312655e-02 -7.9370417e-02\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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 -2.9131625e-02 -1.1060074e-01\n 2.0000000e-02 0.0000000e+00 -0.0000000e+00 0.0000000e+00\n 0.0000000e+00 0.0000000e+00 0.0000000e+00 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, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 100000, "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, "system_info": {"OS": "Linux-5.4.0-137-generic-x86_64-with-glibc2.27 # 154-Ubuntu SMP Thu Jan 5 17:03:22 UTC 2023", "Python": "3.10.8", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1", "GPU Enabled": "True", "Numpy": "1.22.3", "Gym": "0.21.0"}}
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -8.305307834595443, "std_reward": 3.4123792706563814, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-19T12:42:28.742068"}
 
1
+ {"mean_reward": -7.321510564163328, "std_reward": 2.05978472202797, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-19T14:05:55.657841"}