SakataHalmi
commited on
Commit
·
4db12c0
1
Parent(s):
660e177
Initial commit
Browse files- README.md +37 -0
- a2c-PandaReachDense-v3.zip +3 -0
- a2c-PandaReachDense-v3/_stable_baselines3_version +1 -0
- a2c-PandaReachDense-v3/data +97 -0
- a2c-PandaReachDense-v3/policy.optimizer.pth +3 -0
- a2c-PandaReachDense-v3/policy.pth +3 -0
- a2c-PandaReachDense-v3/pytorch_variables.pth +3 -0
- a2c-PandaReachDense-v3/system_info.txt +9 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
- vec_normalize.pkl +3 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- PandaReachDense-v3
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: A2C
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: PandaReachDense-v3
|
16 |
+
type: PandaReachDense-v3
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: -0.19 +/- 0.15
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **A2C** Agent playing **PandaReachDense-v3**
|
25 |
+
This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
|
26 |
+
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
+
|
28 |
+
## Usage (with Stable-baselines3)
|
29 |
+
TODO: Add your code
|
30 |
+
|
31 |
+
|
32 |
+
```python
|
33 |
+
from stable_baselines3 import ...
|
34 |
+
from huggingface_sb3 import load_from_hub
|
35 |
+
|
36 |
+
...
|
37 |
+
```
|
a2c-PandaReachDense-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d102c854d853787f59505f10d9d87cd090726cbcdd0866aa3e8c54226539ac68
|
3 |
+
size 107753
|
a2c-PandaReachDense-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.1.0
|
a2c-PandaReachDense-v3/data
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 0x7fe84744db40>",
|
8 |
+
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc._abc_data object at 0x7fe847450c40>"
|
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": 1696091815538883930,
|
28 |
+
"learning_rate": 0.0007,
|
29 |
+
"tensorboard_log": null,
|
30 |
+
"_last_obs": {
|
31 |
+
":type:": "<class 'collections.OrderedDict'>",
|
32 |
+
":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAACr1wviNvyz5NSBU9Wgivv8c6oT+cNCI/0Wp5PvgyFLuvDdM+0Wp5PvgyFLuvDdM+lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAAaDAov7VamD86+vU9gYp0v1wiyT9hN8s/wObyPlNvmT/dl5m/zoSUPoMlYj/mCZI/lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWYAAAAAAAAAAKvXC+I2/LPk1IFT16GUK/UQvZP69sob5aCK+/xzqhP5w0Ij8Gj2i/JUiKP3CfzT/Rank++DIUu68N0z7Ls/M+CtFsujiswD7Rank++DIUu68N0z7Ls/M+CtFsujiswD6UaA5LBEsGhpRoEnSUUpR1Lg==",
|
33 |
+
"achieved_goal": "[[-0.23509613 0.39733228 0.0364459 ]\n [-1.3674424 1.2596062 0.63361526]\n [ 0.24357153 -0.00226134 0.41221377]\n [ 0.24357153 -0.00226134 0.41221377]]",
|
34 |
+
"desired_goal": "[[-0.6569886 1.1902682 0.12010618]\n [-0.9552384 1.5713611 1.5876275 ]\n [ 0.47441673 1.1987098 -1.199947 ]\n [ 0.29007572 0.8833849 1.1409271 ]]",
|
35 |
+
"observation": "[[-2.3509613e-01 3.9733228e-01 3.6445905e-02 -7.5820124e-01\n 1.6956578e+00 -3.1528232e-01]\n [-1.3674424e+00 1.2596062e+00 6.3361526e-01 -9.0843236e-01\n 1.0803267e+00 1.6064281e+00]\n [ 2.4357153e-01 -2.2613388e-03 4.1221377e-01 4.7598109e-01\n -9.0338348e-04 3.7631392e-01]\n [ 2.4357153e-01 -2.2613388e-03 4.1221377e-01 4.7598109e-01\n -9.0338348e-04 3.7631392e-01]]"
|
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": "[[-0.07005328 -0.1443716 0.27760136]\n [-0.00461807 0.13052414 0.12353627]\n [-0.13075607 -0.05285425 0.29117152]\n [ 0.05506632 0.09264712 0.18514182]]",
|
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:": "gAWV4AsAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKH2UKIwBcpRHv9msT37DVH6MAWyUSwSMAXSUR0Cl4n5ULlV+dX2UKGgGR7+1cpsoDxLCaAdLAmgIR0Cl4ugeJYT1dX2UKGgGR7/SiV0Lc9GJaAdLA2gIR0Cl4rgPuogndX2UKGgGR7/B9itq59VnaAdLAmgIR0Cl4omj0tiAdX2UKGgGR7/Fc+qzZ6D5aAdLA2gIR0Cl4loqkM1CdX2UKGgGR7+5hnanJkoXaAdLAmgIR0Cl4snSOR1YdX2UKGgGR7+90Rvm5lOHaAdLAmgIR0Cl4mtrCWNWdX2UKGgGR7/G9dNWU8msaAdLA2gIR0Cl4v9xyXD4dX2UKGgGR7/XWSEDhcZ+aAdLA2gIR0Cl4qDh99c9dX2UKGgGR7+zVEuxrzoVaAdLAmgIR0Cl4tSvs7dSdX2UKGgGR7/CTUy57PY4aAdLAmgIR0Cl4wjvuw5edX2UKGgGR7/NPZZjhDPXaAdLA2gIR0Cl4noyj59FdX2UKGgGR7/Qjvd/J/5MaAdLA2gIR0Cl4q3izcASdX2UKGgGR7/LjEvTPSlWaAdLA2gIR0Cl4xpRXOnmdX2UKGgGR7/W7VawD/2kaAdLBGgIR0Cl4upRoAXEdX2UKGgGR7/AHgP3BYV7aAdLAmgIR0Cl4rwnQY1pdX2UKGgGR7/RaLGaQV9GaAdLA2gIR0Cl4oxUedTYdX2UKGgGR7+7q0MPSUkfaAdLAmgIR0Cl4scfeUILdX2UKGgGR7/ThJyyUs4DaAdLA2gIR0Cl4ynfEXLvdX2UKGgGR7/SyDZlFtsOaAdLBGgIR0Cl4wGQ8wHrdX2UKGgGR7/Xo7V8Ti84aAdLBGgIR0Cl4qMYl6Z6dX2UKGgGR7/Crjo6jnFHaAdLAmgIR0Cl4zWw3YL9dX2UKGgGR7/D+7UXpGF0aAdLAmgIR0Cl4wlRxcVydX2UKGgGR7/ZlqagElmfaAdLBGgIR0Cl4trmhdt3dX2UKGgGR7+15fMOf/WEaAdLAmgIR0Cl4qrxqfvndX2UKGgGR7/H3BYV6/qPaAdLA2gIR0Cl4xgVO9FndX2UKGgGR7/JvhIe5nUUaAdLA2gIR0Cl4um0NSZSdX2UKGgGR7/OfzSThYNiaAdLA2gIR0Cl4rnlXA/LdX2UKGgGR7/bzq8lHBk7aAdLBWgIR0Cl40x8twrEdX2UKGgGR7+9aJQ+EAYIaAdLAmgIR0Cl4vIRh+fAdX2UKGgGR7/TMVk+X7cgaAdLA2gIR0Cl4yU8V58jdX2UKGgGR7/GICU5dWyUaAdLA2gIR0Cl4sbtJFspdX2UKGgGR7/MDV6NVBD5aAdLA2gIR0Cl41o3R5TqdX2UKGgGR7+ggvDgqEvkaAdLAWgIR0Cl4suVgQYldX2UKGgGR7/BDrqt5le4aAdLAmgIR0Cl4zMGHHmzdX2UKGgGR7/RS+g13t8eaAdLA2gIR0Cl4wSrYGt7dX2UKGgGR7+64OMERraeaAdLAmgIR0Cl42fr0J4TdX2UKGgGR7+4bVBlcyFgaAdLAmgIR0Cl4zv24/eMdX2UKGgGR7/QcBEKE385aAdLA2gIR0Cl4t2Dg62fdX2UKGgGR7/PBj4HoouxaAdLA2gIR0Cl4xH3ta6jdX2UKGgGR7/TvsZ5zHS4aAdLA2gIR0Cl43Uf5k9VdX2UKGgGR7/CfbsWweNlaAdLAmgIR0Cl40UZ3s5XdX2UKGgGR7+Twtrbg0j1aAdLAWgIR0Cl4xar3j+8dX2UKGgGR7/Sw84gieNDaAdLA2gIR0Cl4u3NTtLMdX2UKGgGR7+3TmW+oLofaAdLAmgIR0Cl4yHryDqXdX2UKGgGR7/WV81Gb1AaaAdLA2gIR0Cl44T6rNnodX2UKGgGR7/cHoHLRrrPaAdLBGgIR0Cl41kGJN0vdX2UKGgGR7/Q0QK8cuJ2aAdLA2gIR0Cl4vqBNEgGdX2UKGgGR7/P336AOJ+EaAdLA2gIR0Cl4y4bjtG/dX2UKGgGR7/Ft4zJp35faAdLA2gIR0Cl45UUO/cndX2UKGgGR7/SS13MY/FBaAdLA2gIR0Cl42i5EtuldX2UKGgGR7/Ns3Q2MsH0aAdLA2gIR0Cl4wpJPIn0dX2UKGgGR7/QzUI9kjHGaAdLA2gIR0Cl4z5AQg9vdX2UKGgGR7+2mQ8wHqu9aAdLAmgIR0Cl43CSA6MjdX2UKGgGR7+/5zo2XLNfaAdLAmgIR0Cl4xJDu0CzdX2UKGgGR7/azF+/gzguaAdLBGgIR0Cl46S9VWCFdX2UKGgGR7+j0SRKYiPiaAdLAWgIR0Cl4xZeqrBCdX2UKGgGR7/Q92HLzPKMaAdLA2gIR0Cl44COFQEZdX2UKGgGR7/XM0P6KtPpaAdLBGgIR0Cl41IiTt9hdX2UKGgGR7/SagmJFb3XaAdLA2gIR0Cl47S1NQCTdX2UKGgGR7/VSWZ7XxvvaAdLBGgIR0Cl4yoXTEzgdX2UKGgGR7/NPznRsuWbaAdLA2gIR0Cl440kGA09dX2UKGgGR7/Sv6TGHYYjaAdLA2gIR0Cl417Qb+98dX2UKGgGR7/FDGcWj45+aAdLA2gIR0Cl48To+wC9dX2UKGgGR7+kMVk+X7cgaAdLAWgIR0Cl48kvK2a2dX2UKGgGR7/WccENe+mFaAdLA2gIR0Cl4zqTB68hdX2UKGgGR7/Uqt5le4TcaAdLA2gIR0Cl454YixFBdX2UKGgGR7/O3kxREWqMaAdLA2gIR0Cl42+54GD+dX2UKGgGR7+651/2Cdz5aAdLAmgIR0Cl49MUIsy0dX2UKGgGR7/KpnYg7o0RaAdLA2gIR0Cl40lCkXUIdX2UKGgGR7/NHoX9BKL9aAdLA2gIR0Cl44MJQcghdX2UKGgGR7/OQnQY1pCbaAdLA2gIR0Cl4+XrdFfBdX2UKGgGR7/avsqrilzmaAdLBGgIR0Cl47X0XgtOdX2UKGgGR7+1qpLmITGpaAdLAmgIR0Cl41d7OVxCdX2UKGgGR7/AMH8jzI3jaAdLAmgIR0Cl44vvBrN4dX2UKGgGR7+/zAeq7yxzaAdLAmgIR0Cl42ANoakzdX2UKGgGR7/Ht7a7EpAlaAdLA2gIR0Cl4/LWy1NQdX2UKGgGR7+7tTkyULUkaAdLAmgIR0Cl4/+jmCAddX2UKGgGR7/RzAN5MURGaAdLBWgIR0Cl48/J3gUDdX2UKGgGR7/al9jPOY6XaAdLBGgIR0Cl46FirksCdX2UKGgGR7/QjaPCEYfoaAdLA2gIR0Cl43F/hESedX2UKGgGR7+mNaQmu1WsaAdLAWgIR0Cl46ZhKDkEdX2UKGgGR7/C7YkE9t/GaAdLAmgIR0Cl5AotlI3BdX2UKGgGR7/HZg5R0lqraAdLA2gIR0Cl497HhjvvdX2UKGgGR7/AqDK5kK/maAdLAmgIR0Cl47BpQDV6dX2UKGgGR7/eydFvybx3aAdLBGgIR0Cl44lefI0ZdX2UKGgGR7/Bh4t6HCXQaAdLAmgIR0Cl4745cTrWdX2UKGgGR7/XUHpr1uiwaAdLBGgIR0Cl5CEkB0ZFdX2UKGgGR7/XxXnyNGViaAdLBGgIR0Cl4/RnFo+OdX2UKGgGR7/MuB+WnjyXaAdLA2gIR0Cl45YFA3UAdX2UKGgGR7/RrC3w1BMSaAdLA2gIR0Cl48mIKtxNdX2UKGgGR7/GBwMpgCwKaAdLAmgIR0Cl46GXPZ7HdX2UKGgGR7/Yzu4PPLPlaAdLBGgIR0Cl5DUygwoLdX2UKGgGR7+0+OfdyksSaAdLAmgIR0Cl49abvw3HdX2UKGgGR7+dJ8OTaCcxaAdLAWgIR0Cl46a4c3l0dX2UKGgGR7/aOYplSS/1aAdLBGgIR0Cl5Am/336AdX2UKGgGR7+RwdbPhQ3xaAdLAWgIR0Cl46tcnmaIdX2UKGgGR7+1j7Q9ic5KaAdLAmgIR0Cl5D7jkuHvdX2UKGgGR7/Q8VpKzzEraAdLA2gIR0Cl4+O7g88tdX2UKGgGR7+5VdX1anrIaAdLAmgIR0Cl47POQhfTdWUu"
|
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 |
+
"normalize_advantage": false,
|
69 |
+
"observation_space": {
|
70 |
+
":type:": "<class 'gymnasium.spaces.dict.Dict'>",
|
71 |
+
":serialized:": "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",
|
72 |
+
"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))])",
|
73 |
+
"_shape": null,
|
74 |
+
"dtype": null,
|
75 |
+
"_np_random": null
|
76 |
+
},
|
77 |
+
"action_space": {
|
78 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
79 |
+
":serialized:": "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",
|
80 |
+
"dtype": "float32",
|
81 |
+
"bounded_below": "[ True True True]",
|
82 |
+
"bounded_above": "[ True True True]",
|
83 |
+
"_shape": [
|
84 |
+
3
|
85 |
+
],
|
86 |
+
"low": "[-1. -1. -1.]",
|
87 |
+
"high": "[1. 1. 1.]",
|
88 |
+
"low_repr": "-1.0",
|
89 |
+
"high_repr": "1.0",
|
90 |
+
"_np_random": "Generator(PCG64)"
|
91 |
+
},
|
92 |
+
"n_envs": 4,
|
93 |
+
"lr_schedule": {
|
94 |
+
":type:": "<class 'function'>",
|
95 |
+
":serialized:": "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"
|
96 |
+
}
|
97 |
+
}
|
a2c-PandaReachDense-v3/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f22e68656a0681d79f46e93e64b4fc80cf83ff82e1eae389e50ccafc77afb28d
|
3 |
+
size 44734
|
a2c-PandaReachDense-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ce07c55c61cd232a1f8a31cf45ebe691ce8b6017d03ab82af9fb843c561e4dd
|
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-5.10.16.3-microsoft-standard-WSL2-x86_64-with-glibc2.27 # 1 SMP Fri Apr 2 22:23:49 UTC 2021
|
2 |
+
- Python: 3.10.13
|
3 |
+
- Stable-Baselines3: 2.1.0
|
4 |
+
- PyTorch: 2.0.1+cu117
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.26.0
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.28.1
|
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 0x7fe84744db40>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7fe847450c40>"}, "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": 1696091815538883930, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[-0.23509613 0.39733228 0.0364459 ]\n [-1.3674424 1.2596062 0.63361526]\n [ 0.24357153 -0.00226134 0.41221377]\n [ 0.24357153 -0.00226134 0.41221377]]", "desired_goal": "[[-0.6569886 1.1902682 0.12010618]\n [-0.9552384 1.5713611 1.5876275 ]\n [ 0.47441673 1.1987098 -1.199947 ]\n [ 0.29007572 0.8833849 1.1409271 ]]", "observation": "[[-2.3509613e-01 3.9733228e-01 3.6445905e-02 -7.5820124e-01\n 1.6956578e+00 -3.1528232e-01]\n [-1.3674424e+00 1.2596062e+00 6.3361526e-01 -9.0843236e-01\n 1.0803267e+00 1.6064281e+00]\n [ 2.4357153e-01 -2.2613388e-03 4.1221377e-01 4.7598109e-01\n -9.0338348e-04 3.7631392e-01]\n [ 2.4357153e-01 -2.2613388e-03 4.1221377e-01 4.7598109e-01\n -9.0338348e-04 3.7631392e-01]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.07005328 -0.1443716 0.27760136]\n [-0.00461807 0.13052414 0.12353627]\n [-0.13075607 -0.05285425 0.29117152]\n [ 0.05506632 0.09264712 0.18514182]]", "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": "Generator(PCG64)"}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "system_info": {"OS": "Linux-5.10.16.3-microsoft-standard-WSL2-x86_64-with-glibc2.27 # 1 SMP Fri Apr 2 22:23:49 UTC 2021", "Python": "3.10.13", "Stable-Baselines3": "2.1.0", "PyTorch": "2.0.1+cu117", "GPU Enabled": "True", "Numpy": "1.26.0", "Cloudpickle": "2.2.1", "Gymnasium": "0.28.1", "OpenAI Gym": "0.26.2"}}
|
replay.mp4
ADDED
Binary file (682 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -0.18855011463165283, "std_reward": 0.1505905699424316, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-30T17:30:02.787588"}
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebedeeabd7112c88eefdfe2eafd03892ac7ecac2176b9549d69d4147b0974c0b
|
3 |
+
size 3080
|