Hugging Face's logo

CJJ1234
/
a2c-PandaReachDense-v3

Reinforcement Learning
stable-baselines3
PandaReachDense-v3
deep-reinforcement-learning
Eval Results
Model card Files Community
CJJ1234 commited on
Commit
7a374ec
•
1 Parent(s): 95fa9c8

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 +14 -14
  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: -0.21 +/- 0.13
20
  name: mean_reward
21
  verified: false
22
  ---
 
16
  type: PandaReachDense-v3
17
  metrics:
18
  - type: mean_reward
19
+ value: -12.18 +/- 3.12
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 sha256:9ac82f667a9e54bfe15d98d7133e4bf49a313a022f5d161f99245ad622aeccbf
3
- size 106832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bd47397ab48a7c7627faf0162a305ca036e02fa0c85980aaef0236583051298
3
+ size 102812
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 0x786d5d7652d0>",
8
  "__abstractmethods__": "frozenset()",
9
- "_abc_impl": "<_abc._abc_data object at 0x786d5d56c700>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
@@ -19,30 +19,30 @@
19
  "weight_decay": 0
20
  }
21
  },
22
- "num_timesteps": 1000000,
23
- "_total_timesteps": 1000000,
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
- "start_time": 1695682450785331309,
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": "[[-0.09408766 0.38508433 -0.19570313]\n [-0.59469587 -0.15841512 0.31337723]\n [ 0.25483403 -0.01404675 0.42351803]\n [-0.08004477 0.3851643 -0.20013238]]",
34
- "desired_goal": "[[-0.09282999 1.4399315 -0.5526888 ]\n [-0.67169106 -0.19831917 0.9115996 ]\n [ 1.0767 -0.57681394 1.0213834 ]\n [ 0.00746666 1.448476 -1.1862028 ]]",
35
- "observation": "[[-0.09408766 0.38508433 -0.19570313 -1.8807292 1.6700772 -1.3859677 ]\n [-0.59469587 -0.15841512 0.31337723 -0.9352089 -0.12279911 0.82150775]\n [ 0.25483403 -0.01404675 0.42351803 0.46859244 -0.00343198 0.37526152]\n [-0.08004477 0.3851643 -0.20013238 -1.860142 1.6674571 -1.3598834 ]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
39
- ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[ 0.14549991 0.08802837 0.1511928 ]\n [ 0.06355038 -0.07407507 0.19397143]\n [ 0.00422189 0.06556902 0.25478628]\n [-0.08636669 0.12576187 0.16670176]]",
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,
@@ -52,13 +52,13 @@
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": 50000,
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 0x7e00e054dc60>",
8
  "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7e00e053ef80>"
10
  },
11
  "verbose": 1,
12
  "policy_kwargs": {
 
19
  "weight_decay": 0
20
  }
21
  },
22
+ "num_timesteps": 100,
23
+ "_total_timesteps": 100,
24
  "_num_timesteps_at_start": 0,
25
  "seed": null,
26
  "action_noise": null,
27
+ "start_time": 1695932613827333441,
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": "[[ 0.02551983 0.05396058 -1.0202416 ]\n [-2.8857658 1.2591623 -1.1073071 ]\n [ 0.94104123 -1.7689784 -1.244321 ]\n [-0.416241 -0.3756322 -1.2661525 ]]",
34
+ "desired_goal": "[[ 1.5871334 -1.0287097 -0.23926106]\n [-0.8179085 1.6119032 1.1651586 ]\n [ 0.1231938 -0.5815292 0.5752986 ]\n [-0.89242035 -0.00165835 -1.5011896 ]]",
35
+ "observation": "[[ 0.02551983 0.05396058 -1.0202416 1.0157958 -1.5262525 1.7924914 ]\n [-2.8857658 1.2591623 -1.1073071 -0.28966087 0.19222008 0.5730499 ]\n [ 0.94104123 -1.7689784 -1.244321 0.73406553 0.14991811 0.19087988]\n [-0.416241 -0.3756322 -1.2661525 0.39802542 -1.0514468 0.22816278]]"
36
  },
37
  "_last_episode_starts": {
38
  ":type:": "<class 'numpy.ndarray'>",
39
+ ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[ 0.10649096 0.0142692 0.10837334]\n [-0.11817395 0.08550552 0.22003835]\n [-0.03026169 0.02633287 0.17313875]\n [-0.12513441 0.04197616 0.00803777]]",
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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
56
  },
57
  "ep_success_buffer": {
58
  ":type:": "<class 'collections.deque'>",
59
  ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
60
  },
61
+ "_n_updates": 5,
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 sha256:4f7771561471f9f0b617b32bd587501e0010b4cdce165b821d35695910492bf4
3
  size 44734
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a4598eed8bdb62f08df9dbb05aefd7c14731afd14c02f88714963466d922f0
3
  size 44734
a2c-PandaReachDense-v3/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36e0bb1fa663f55d31ad4e1951050222eccf3f45840f560779848ebe3a125f36
3
  size 46014
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f62d9dc4eca40fa9948cd367dd68216d90dfe12117d3df8146bda04238ce649
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 0x786d5d7652d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x786d5d56c700>"}, "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": 1695682450785331309, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.09408766 0.38508433 -0.19570313]\n [-0.59469587 -0.15841512 0.31337723]\n [ 0.25483403 -0.01404675 0.42351803]\n [-0.08004477 0.3851643 -0.20013238]]", "desired_goal": "[[-0.09282999 1.4399315 -0.5526888 ]\n [-0.67169106 -0.19831917 0.9115996 ]\n [ 1.0767 -0.57681394 1.0213834 ]\n [ 0.00746666 1.448476 -1.1862028 ]]", "observation": "[[-0.09408766 0.38508433 -0.19570313 -1.8807292 1.6700772 -1.3859677 ]\n [-0.59469587 -0.15841512 0.31337723 -0.9352089 -0.12279911 0.82150775]\n [ 0.25483403 -0.01404675 0.42351803 0.46859244 -0.00343198 0.37526152]\n [-0.08004477 0.3851643 -0.20013238 -1.860142 1.6674571 -1.3598834 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[ 0.14549991 0.08802837 0.1511928 ]\n [ 0.06355038 -0.07407507 0.19397143]\n [ 0.00422189 0.06556902 0.25478628]\n [-0.08636669 0.12576187 0.16670176]]", "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-5.15.120+-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": "True", "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 0x7e00e054dc60>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7e00e053ef80>"}, "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": 100, "_total_timesteps": 100, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1695932613827333441, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.02551983 0.05396058 -1.0202416 ]\n [-2.8857658 1.2591623 -1.1073071 ]\n [ 0.94104123 -1.7689784 -1.244321 ]\n [-0.416241 -0.3756322 -1.2661525 ]]", "desired_goal": "[[ 1.5871334 -1.0287097 -0.23926106]\n [-0.8179085 1.6119032 1.1651586 ]\n [ 0.1231938 -0.5815292 0.5752986 ]\n [-0.89242035 -0.00165835 -1.5011896 ]]", "observation": "[[ 0.02551983 0.05396058 -1.0202416 1.0157958 -1.5262525 1.7924914 ]\n [-2.8857658 1.2591623 -1.1073071 -0.28966087 0.19222008 0.5730499 ]\n [ 0.94104123 -1.7689784 -1.244321 0.73406553 0.14991811 0.19087988]\n [-0.416241 -0.3756322 -1.2661525 0.39802542 -1.0514468 0.22816278]]"}, "_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": "[[ 0.10649096 0.0142692 0.10837334]\n [-0.11817395 0.08550552 0.22003835]\n [-0.03026169 0.02633287 0.17313875]\n [-0.12513441 0.04197616 0.00803777]]", "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:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 5, "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": "True", "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": -0.21321067931130527, "std_reward": 0.1327001162419402, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-25T23:53:25.287113"}
 
1
+ {"mean_reward": -12.182014126330614, "std_reward": 3.1216546400358958, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-28T20:32:40.659056"}
vec_normalize.pkl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a7f9a008d2826ea954c88901f5952360b1883db6ab340bc3ec9592be3c77847
3
  size 2623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945a5cf727fb4ddd96f8634747aab078c776e7c1f112af4cccac15e1a851200a
3
  size 2623