Commit
•
c91ca00
1
Parent(s):
0942721
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 +112 -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 +/- 0.10
|
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 sha256:45f2360a6002b6be9e81f0caad0632698611e0ea9e295cf5fb1de707b3291b3b
|
3 |
+
size 110366
|
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 0x7b6604277010>",
|
8 |
+
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc._abc_data object at 0x7b660426bb40>"
|
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": 250000,
|
23 |
+
"_total_timesteps": 250000,
|
24 |
+
"_num_timesteps_at_start": 0,
|
25 |
+
"seed": null,
|
26 |
+
"action_noise": null,
|
27 |
+
"start_time": 1711842651814775273,
|
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": "[[-0.05719506 -0.3708502 -0.1109267 ]\n [ 0.25427315 0.00127384 0.43429857]\n [ 0.25427315 0.00127384 0.43429857]\n [-1.188482 -0.7120754 0.608318 ]]",
|
34 |
+
"desired_goal": "[[-1.3973026 -0.5523115 -0.8995225 ]\n [-0.52599734 -0.81282324 -1.5077151 ]\n [ 0.20158611 0.85008115 -0.658218 ]\n [-1.4886128 -0.49062222 0.7236107 ]]",
|
35 |
+
"observation": "[[-5.71950637e-02 -3.70850205e-01 -1.10926695e-01 -1.79855144e+00\n -1.69568253e+00 -1.39878166e+00]\n [ 2.54273146e-01 1.27383543e-03 4.34298575e-01 4.18759167e-01\n -5.18617313e-03 3.55794996e-01]\n [ 2.54273146e-01 1.27383543e-03 4.34298575e-01 4.18759167e-01\n -5.18617313e-03 3.55794996e-01]\n [-1.18848205e+00 -7.12075412e-01 6.08317971e-01 -9.15991247e-01\n 1.03302099e-01 1.46514130e+00]]"
|
36 |
+
},
|
37 |
+
"_last_episode_starts": {
|
38 |
+
":type:": "<class 'numpy.ndarray'>",
|
39 |
+
":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.08510933 0.05653607 0.21527286]\n [ 0.02095913 0.06166939 0.24512403]\n [ 0.12135995 0.10526579 0.12470362]\n [ 0.01881569 0.04761177 0.28579247]]",
|
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": 12500,
|
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 0x7b66041cd990>",
|
75 |
+
"reset": "<function DictRolloutBuffer.reset at 0x7b66041cda20>",
|
76 |
+
"add": "<function DictRolloutBuffer.add at 0x7b66041cdab0>",
|
77 |
+
"get": "<function DictRolloutBuffer.get at 0x7b66041cdb40>",
|
78 |
+
"_get_samples": "<function DictRolloutBuffer._get_samples at 0x7b66041cdbd0>",
|
79 |
+
"__abstractmethods__": "frozenset()",
|
80 |
+
"_abc_impl": "<_abc._abc_data object at 0x7b66041ca300>"
|
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:b5d5d5790b3d0e21f69358e75af51ed6dc112b231df75f32cb163f57024e4e25
|
3 |
+
size 45167
|
a2c-PandaReachDense-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dca835161fca824c34f5c443c078fd298bf4de9721eb30ac8b86acce0b99e6a8
|
3 |
+
size 46447
|
a2c-PandaReachDense-v3/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
a2c-PandaReachDense-v3/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.2.1
|
4 |
+
- PyTorch: 2.2.1+cu121
|
5 |
+
- GPU Enabled: True
|
6 |
+
- Numpy: 1.25.2
|
7 |
+
- Cloudpickle: 2.2.1
|
8 |
+
- Gymnasium: 0.29.1
|
9 |
+
- OpenAI Gym: 0.25.2
|
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 0x7b6604277010>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b660426bb40>"}, "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": 250000, "_total_timesteps": 250000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1711842651814775273, "learning_rate": 0.0007, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "gAWVuwEAAAAAAACMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwSbnVtcHkuY29yZS5udW1lcmljlIwLX2Zyb21idWZmZXKUk5QoljAAAAAAAAAAX0VqvRTgvb6JLeO9FzCCPtP2pjpiXN4+FzCCPtP2pjpiXN4+LiCYv5NKNr+6uhs/lIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYksESwOGlIwBQ5R0lFKUjAxkZXNpcmVkX2dvYWyUaAcoljAAAAAAAAAA0Nqyv0lkDb8bR2a/w6cGvy8VUL/P/MC/l2xOPuueWT/6gCi/3Yq+v9Yy+76NPjk/lGgOSwRLA4aUaBJ0lFKUjAtvYnNlcnZhdGlvbpRoByiWYAAAAAAAAABfRWq9FOC9vokt473vNua/IAzZv0cLs78XMII+0/amOmJc3j6aZ9Y+xvCpu8Mqtj4XMII+0/amOmJc3j6aZ9Y+xvCpu8Mqtj4uIJi/k0o2v7q6Gz9nfmq/DZDTPcCJuz+UaA5LBEsGhpRoEnSUUpR1Lg==", "achieved_goal": "[[-0.05719506 -0.3708502 -0.1109267 ]\n [ 0.25427315 0.00127384 0.43429857]\n [ 0.25427315 0.00127384 0.43429857]\n [-1.188482 -0.7120754 0.608318 ]]", "desired_goal": "[[-1.3973026 -0.5523115 -0.8995225 ]\n [-0.52599734 -0.81282324 -1.5077151 ]\n [ 0.20158611 0.85008115 -0.658218 ]\n [-1.4886128 -0.49062222 0.7236107 ]]", "observation": "[[-5.71950637e-02 -3.70850205e-01 -1.10926695e-01 -1.79855144e+00\n -1.69568253e+00 -1.39878166e+00]\n [ 2.54273146e-01 1.27383543e-03 4.34298575e-01 4.18759167e-01\n -5.18617313e-03 3.55794996e-01]\n [ 2.54273146e-01 1.27383543e-03 4.34298575e-01 4.18759167e-01\n -5.18617313e-03 3.55794996e-01]\n [-1.18848205e+00 -7.12075412e-01 6.08317971e-01 -9.15991247e-01\n 1.03302099e-01 1.46514130e+00]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAABAQCUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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": "[[-0.08510933 0.05653607 0.21527286]\n [ 0.02095913 0.06166939 0.24512403]\n [ 0.12135995 0.10526579 0.12470362]\n [ 0.01881569 0.04761177 0.28579247]]", "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": 12500, "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 0x7b66041cd990>", "reset": "<function DictRolloutBuffer.reset at 0x7b66041cda20>", "add": "<function DictRolloutBuffer.add at 0x7b66041cdab0>", "get": "<function DictRolloutBuffer.get at 0x7b66041cdb40>", "_get_samples": "<function DictRolloutBuffer._get_samples at 0x7b66041cdbd0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7b66041ca300>"}, "rollout_buffer_kwargs": {}, "normalize_advantage": false, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "gAWVsAMAAAAAAACMFWd5bW5hc2l1bS5zcGFjZXMuZGljdJSMBERpY3SUk5QpgZR9lCiMBnNwYWNlc5SMC2NvbGxlY3Rpb25zlIwLT3JkZXJlZERpY3SUk5QpUpQojA1hY2hpZXZlZF9nb2FslIwUZ3ltbmFzaXVtLnNwYWNlcy5ib3iUjANCb3iUk5QpgZR9lCiMBWR0eXBllIwFbnVtcHmUjAVkdHlwZZSTlIwCZjSUiYiHlFKUKEsDjAE8lE5OTkr/////Sv////9LAHSUYowNYm91bmRlZF9iZWxvd5SMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYDAAAAAAAAAAEBAZRoE4wCYjGUiYiHlFKUKEsDjAF8lE5OTkr/////Sv////9LAHSUYksDhZSMAUOUdJRSlIwNYm91bmRlZF9hYm92ZZRoHCiWAwAAAAAAAAABAQGUaCBLA4WUaCR0lFKUjAZfc2hhcGWUSwOFlIwDbG93lGgcKJYMAAAAAAAAAAAAIMEAACDBAAAgwZRoFksDhZRoJHSUUpSMBGhpZ2iUaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlIwIbG93X3JlcHKUjAUtMTAuMJSMCWhpZ2hfcmVwcpSMBDEwLjCUjApfbnBfcmFuZG9tlE51YowMZGVzaXJlZF9nb2FslGgNKYGUfZQoaBBoFmgZaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgnaBwolgMAAAAAAAAAAQEBlGggSwOFlGgkdJRSlGgsSwOFlGguaBwolgwAAAAAAAAAAAAgwQAAIMEAACDBlGgWSwOFlGgkdJRSlGgzaBwolgwAAAAAAAAAAAAgQQAAIEEAACBBlGgWSwOFlGgkdJRSlGg4jAUtMTAuMJRoOowEMTAuMJRoPE51YowLb2JzZXJ2YXRpb26UaA0pgZR9lChoEGgWaBloHCiWBgAAAAAAAAABAQEBAQGUaCBLBoWUaCR0lFKUaCdoHCiWBgAAAAAAAAABAQEBAQGUaCBLBoWUaCR0lFKUaCxLBoWUaC5oHCiWGAAAAAAAAAAAACDBAAAgwQAAIMEAACDBAAAgwQAAIMGUaBZLBoWUaCR0lFKUaDNoHCiWGAAAAAAAAAAAACBBAAAgQQAAIEEAACBBAAAgQQAAIEGUaBZLBoWUaCR0lFKUaDiMBS0xMC4wlGg6jAQxMC4wlGg8TnVidWgsTmgQTmg8TnViLg==", "spaces": "OrderedDict([('achieved_goal', Box(-10.0, 10.0, (3,), float32)), ('desired_goal', Box(-10.0, 10.0, (3,), float32)), ('observation', Box(-10.0, 10.0, (6,), float32))])", "_shape": null, "dtype": null, "_np_random": null}, "action_space": {":type:": "<class 'gymnasium.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True True True]", "bounded_above": "[ True True True]", "_shape": [3], "low": "[-1. -1. -1.]", "high": "[1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVxQIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSS91c3IvbG9jYWwvbGliL3B5dGhvbjMuMTAvZGlzdC1wYWNrYWdlcy9zdGFibGVfYmFzZWxpbmVzMy9jb21tb24vdXRpbHMucHmUjARmdW5jlEuDQwIEAZSMA3ZhbJSFlCl0lFKUfZQojAtfX3BhY2thZ2VfX5SMGHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbpSMCF9fbmFtZV9flIwec3RhYmxlX2Jhc2VsaW5lczMuY29tbW9uLnV0aWxzlIwIX19maWxlX1+UjEkvdXNyL2xvY2FsL2xpYi9weXRob24zLjEwL2Rpc3QtcGFja2FnZXMvc3RhYmxlX2Jhc2VsaW5lczMvY29tbW9uL3V0aWxzLnB5lHVOTmgAjBBfbWFrZV9lbXB0eV9jZWxslJOUKVKUhZR0lFKUjBxjbG91ZHBpY2tsZS5jbG91ZHBpY2tsZV9mYXN0lIwSX2Z1bmN0aW9uX3NldHN0YXRllJOUaB99lH2UKGgWaA2MDF9fcXVhbG5hbWVfX5SMGWNvbnN0YW50X2ZuLjxsb2NhbHM+LmZ1bmOUjA9fX2Fubm90YXRpb25zX1+UfZSMDl9fa3dkZWZhdWx0c19flE6MDF9fZGVmYXVsdHNfX5ROjApfX21vZHVsZV9flGgXjAdfX2RvY19flE6MC19fY2xvc3VyZV9flGgAjApfbWFrZV9jZWxslJOURz9G8AaNuLrHhZRSlIWUjBdfY2xvdWRwaWNrbGVfc3VibW9kdWxlc5RdlIwLX19nbG9iYWxzX1+UfZR1hpSGUjAu"}, "system_info": {"OS": "Linux-6.1.58+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sat Nov 18 15:31:17 UTC 2023", "Python": "3.10.12", "Stable-Baselines3": "2.2.1", "PyTorch": "2.2.1+cu121", "GPU Enabled": "True", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
|
replay.mp4
ADDED
Binary file (676 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -0.19188243462704122, "std_reward": 0.10288407184843275, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-31T00:07:46.884098"}
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:808fed51e81120eb5f0753deca1655c1d30f0e9317d8f9a32c93c7ebbc50745a
|
3 |
+
size 2659
|