Hugging Face's logo

forgedRice
/
a2c-PandaReachDense-v3

Reinforcement Learning
stable-baselines3
PandaReachDense-v3
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
Community
forgedRice commited on
Commit
ca4e07c
·
verified ·
1 Parent(s): e163a44

PandaReachDense model

Browse files
Files changed (12) hide show
  1. .gitattributes +35 -35
  2. README.md +35 -0
  3. a2c-PandaReachDense-v3.zip +3 -0
  4. a2c-PandaReachDense-v3/_stable_baselines3_version +1 -0
  5. a2c-PandaReachDense-v3/data +112 -0
  6. a2c-PandaReachDense-v3/policy.optimizer.pth +3 -0
  7. a2c-PandaReachDense-v3/policy.pth +3 -0
  8. a2c-PandaReachDense-v3/pytorch_variables.pth +3 -0
  9. a2c-PandaReachDense-v3/system_info.txt +9 -0
  10. config.json +1 -0
  11. results.json +1 -0
  12. vec_normalize.pkl +3 -0
.gitattributes CHANGED
@@ -1,35 +1,35 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz filter=lfs diff=lfs merge=lfs -text
33
- *.zip filter=lfs diff=lfs merge=lfs -text
34
- *.zst filter=lfs diff=lfs merge=lfs -text
35
- *tfevents* filter=lfs diff=lfs merge=lfs -text
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz filter=lfs diff=lfs merge=lfs -text
33
+ *.zip filter=lfs diff=lfs merge=lfs -text
34
+ *.zst filter=lfs diff=lfs merge=lfs -text
35
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - PandaReachDense-v3
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ - A2C
9
+ - robotics
10
+ - panda-gym
11
+ model-index:
12
+ - name: A2C
13
+ results:
14
+ - task:
15
+ type: reinforcement-learning
16
+ name: reinforcement-learning
17
+ dataset:
18
+ name: PandaReachDense-v3
19
+ type: PandaReachDense-v3
20
+ metrics:
21
+ - type: mean_reward
22
+ value: -2.85 +/- 0.75
23
+ name: mean_reward
24
+ verified: false
25
+ ---
26
+
27
+ # A2C Agent playing PandaReachDense-v3
28
+
29
+ This is a trained A2C agent playing PandaReachDense-v3 using stable-baselines3 and panda-gym.
30
+
31
+ The robotic arm learns to place its end-effector at a target position using Advantage Actor-Critic with MultiInputPolicy and VecNormalize wrapper.
32
+
33
+ **Training**: 1,000,000 timesteps
34
+ **Environment**: Dense reward robotic reaching task
35
+ **Performance**: Mean reward -2.85 ± 0.75
a2c-PandaReachDense-v3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b164fc4eb04f553f415265fba3800e4a6326120dfe2faba6f31161e75abb5a
3
+ size 108989
a2c-PandaReachDense-v3/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 2.2.1
a2c-PandaReachDense-v3/data ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "policy_class": {
3
+ ":type:": "<class 'abc.ABCMeta'>",
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 0x7ff2a2c51900>",
8
+ "__abstractmethods__": "frozenset()",
9
+ "_abc_impl": "<_abc._abc_data object at 0x7ff2a2c54a00>"
10
+ },
11
+ "verbose": 1,
12
+ "policy_kwargs": {
13
+ ":type:": "<class 'dict'>",
14
+ ":serialized:": "gAWVgQAAAAAAAAB9lCiMD29wdGltaXplcl9jbGFzc5SME3RvcmNoLm9wdGltLnJtc3Byb3CUjAdSTVNwcm9wlJOUjBBvcHRpbWl6ZXJfa3dhcmdzlH2UKIwFYWxwaGGURz/vrhR64UeujANlcHOURz7k+LWI42jxjAx3ZWlnaHRfZGVjYXmUSwB1dS4=",
15
+ "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>",
16
+ "optimizer_kwargs": {
17
+ "alpha": 0.99,
18
+ "eps": 1e-05,
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": 1701521395557864031,
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": "[[ 0.28680396 -0.00350927 0.43270287]\n [ 1.0954406 0.46639153 0.24649441]\n [ 1.0989183 -0.42644486 0.25434482]\n [ 0.6271266 -0.43168882 0.68156475]]",
34
+ "desired_goal": "[[-1.3620702 -1.0334246 0.29616672]\n [ 0.856488 1.3414397 -0.17350589]\n [ 1.5397626 -1.3329157 0.04086327]\n [ 1.6139685 -0.9999701 1.2896942 ]]",
35
+ "observation": "[[ 2.8680396e-01 -3.5092665e-03 4.3270287e-01 4.9008968e-01\n 1.2529044e-03 3.8603929e-01]\n [ 1.0954406e+00 4.6639153e-01 2.4649441e-01 1.5862322e+00\n 1.6259631e+00 -1.1550289e+00]\n [ 1.0989183e+00 -4.2644486e-01 2.5434482e-01 1.6158699e+00\n -1.5493209e+00 -1.1248903e+00]\n [ 6.2712657e-01 -4.3168882e-01 6.8156475e-01 1.6962389e+00\n -1.5651786e+00 1.1280876e+00]]"
36
+ },
37
+ "_last_episode_starts": {
38
+ ":type:": "<class 'numpy.ndarray'>",
39
+ ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.02972577 0.13940527 0.03997856]\n [ 0.09575883 0.09257074 0.1986251 ]\n [ 0.09539963 0.02161054 0.23303588]\n [ 0.0063214 0.11326997 0.07071205]]",
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": 50000,
62
+ "n_steps": 5,
63
+ "gamma": 0.99,
64
+ "gae_lambda": 1.0,
65
+ "ent_coef": 0.0,
66
+ "vf_coef": 0.5,
67
+ "max_grad_norm": 0.5,
68
+ "rollout_buffer_class": {
69
+ ":type:": "<class 'abc.ABCMeta'>",
70
+ ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu",
71
+ "__module__": "stable_baselines3.common.buffers",
72
+ "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}",
73
+ "__doc__": "\n Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n Extends the RolloutBuffer to use dictionary observations\n\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to Monte-Carlo advantage estimate when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ",
74
+ "__init__": "<function DictRolloutBuffer.__init__ at 0x7ff2a2ee43a0>",
75
+ "reset": "<function DictRolloutBuffer.reset at 0x7ff2a2ee4430>",
76
+ "add": "<function DictRolloutBuffer.add at 0x7ff2a2ee44c0>",
77
+ "get": "<function DictRolloutBuffer.get at 0x7ff2a2ee4550>",
78
+ "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7ff2a2ee45e0>",
79
+ "__abstractmethods__": "frozenset()",
80
+ "_abc_impl": "<_abc._abc_data object at 0x7ff2a2ecf480>"
81
+ },
82
+ "rollout_buffer_kwargs": {},
83
+ "normalize_advantage": false,
84
+ "observation_space": {
85
+ ":type:": "<class 'gymnasium.spaces.dict.Dict'>",
86
+ ":serialized:": "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",
87
+ "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])",
88
+ "_shape": null,
89
+ "dtype": null,
90
+ "_np_random": null
91
+ },
92
+ "action_space": {
93
+ ":type:": "<class 'gymnasium.spaces.box.Box'>",
94
+ ":serialized:": "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",
95
+ "dtype": "float32",
96
+ "bounded_below": "[ True True True]",
97
+ "bounded_above": "[ True True True]",
98
+ "_shape": [
99
+ 3
100
+ ],
101
+ "low": "[-1. -1. -1.]",
102
+ "high": "[1. 1. 1.]",
103
+ "low_repr": "-1.0",
104
+ "high_repr": "1.0",
105
+ "_np_random": null
106
+ },
107
+ "n_envs": 4,
108
+ "lr_schedule": {
109
+ ":type:": "<class 'function'>",
110
+ ":serialized:": "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"
111
+ }
112
+ }
a2c-PandaReachDense-v3/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a615364d1ef88383c56e0c9200ffefb430e2a299e0e1bfb820209afdb439fc
3
+ size 44734
a2c-PandaReachDense-v3/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d65274fc0c023ff5d10a4f837c926db815ffdb5caa4bd144bb4226cb086becf
3
+ size 46014
a2c-PandaReachDense-v3/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
a2c-PandaReachDense-v3/system_info.txt ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.15.133+-x86_64-with-glibc2.35 # 1 SMP Sun Nov 19 12:52:09 UTC 2023
2
+ - Python: 3.10.12
3
+ - Stable-Baselines3: 2.2.1
4
+ - PyTorch: 2.0.0
5
+ - GPU Enabled: True
6
+ - Numpy: 1.24.3
7
+ - Cloudpickle: 3.0.0
8
+ - Gymnasium: 0.29.1
9
+ - OpenAI Gym: 0.26.2
config.json ADDED
@@ -0,0 +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 0x7ff2a2c51900>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff2a2c54a00>"}, "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": 1701521395557864031, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.28680396 -0.00350927 0.43270287]\n [ 1.0954406 0.46639153 0.24649441]\n [ 1.0989183 -0.42644486 0.25434482]\n [ 0.6271266 -0.43168882 0.68156475]]", "desired_goal": "[[-1.3620702 -1.0334246 0.29616672]\n [ 0.856488 1.3414397 -0.17350589]\n [ 1.5397626 -1.3329157 0.04086327]\n [ 1.6139685 -0.9999701 1.2896942 ]]", "observation": "[[ 2.8680396e-01 -3.5092665e-03 4.3270287e-01 4.9008968e-01\n 1.2529044e-03 3.8603929e-01]\n [ 1.0954406e+00 4.6639153e-01 2.4649441e-01 1.5862322e+00\n 1.6259631e+00 -1.1550289e+00]\n [ 1.0989183e+00 -4.2644486e-01 2.5434482e-01 1.6158699e+00\n -1.5493209e+00 -1.1248903e+00]\n [ 6.2712657e-01 -4.3168882e-01 6.8156475e-01 1.6962389e+00\n -1.5651786e+00 1.1280876e+00]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.02972577 0.13940527 0.03997856]\n [ 0.09575883 0.09257074 0.1986251 ]\n [ 0.09539963 0.02161054 0.23303588]\n [ 0.0063214 0.11326997 0.07071205]]", "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, "rollout_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOgAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwRRGljdFJvbGxvdXRCdWZmZXKUk5Qu", "__module__": "stable_baselines3.common.buffers", "__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n Dict Rollout buffer used in on-policy algorithms like A2C/PPO.\n Extends the RolloutBuffer to use dictionary observations\n\n It corresponds to ``buffer_size`` transitions collected\n using the current policy.\n This experience will be discarded after the policy update.\n In order to use PPO objective, we also store the current value of each state\n and the log probability of each taken action.\n\n The term rollout here refers to the model-free notion and should not\n be used with the concept of rollout used in model-based RL or planning.\n Hence, it is only involved in policy and value function training but not action selection.\n\n :param buffer_size: Max number of element in the buffer\n :param observation_space: Observation space\n :param action_space: Action space\n :param device: PyTorch device\n :param gae_lambda: Factor for trade-off of bias vs variance for Generalized Advantage Estimator\n Equivalent to Monte-Carlo advantage estimate when set to 1.\n :param gamma: Discount factor\n :param n_envs: Number of parallel environments\n ", "__init__": "<function DictRolloutBuffer.__init__ at 0x7ff2a2ee43a0>", "reset": "<function DictRolloutBuffer.reset at 0x7ff2a2ee4430>", "add": "<function DictRolloutBuffer.add at 0x7ff2a2ee44c0>", "get": "<function DictRolloutBuffer.get at 0x7ff2a2ee4550>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7ff2a2ee45e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7ff2a2ecf480>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.15.133+-x86_64-with-glibc2.35 # 1 SMP Sun Nov 19 12:52:09 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.0.0", "GPU Enabled": "True", "Numpy": "1.24.3", "Cloudpickle": "3.0.0", "Gymnasium": "0.29.1", "OpenAI Gym": "0.26.2"}}
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": -0.3882879420183599, "std_reward": 0.5240187832690235, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-09-27T13:40:56.729968"}
vec_normalize.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3513bcb6be87b379a956d62f51b9182c40ae969ba98dcf98a9ddb6667f1fd902
3
+ size 2659