Initial commit
Browse files- README.md +37 -0
- config.json +1 -0
- replay.mp4 +0 -0
- results.json +1 -0
- td3-FetchPickAndPlaceDense-v2.zip +3 -0
- td3-FetchPickAndPlaceDense-v2/_stable_baselines3_version +1 -0
- td3-FetchPickAndPlaceDense-v2/actor.optimizer.pth +3 -0
- td3-FetchPickAndPlaceDense-v2/critic.optimizer.pth +3 -0
- td3-FetchPickAndPlaceDense-v2/data +99 -0
- td3-FetchPickAndPlaceDense-v2/policy.pth +3 -0
- td3-FetchPickAndPlaceDense-v2/pytorch_variables.pth +3 -0
- td3-FetchPickAndPlaceDense-v2/system_info.txt +9 -0
README.md
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- FetchPickAndPlaceDense-v2
|
5 |
+
- deep-reinforcement-learning
|
6 |
+
- reinforcement-learning
|
7 |
+
- stable-baselines3
|
8 |
+
model-index:
|
9 |
+
- name: TD3
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
type: reinforcement-learning
|
13 |
+
name: reinforcement-learning
|
14 |
+
dataset:
|
15 |
+
name: FetchPickAndPlaceDense-v2
|
16 |
+
type: FetchPickAndPlaceDense-v2
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: -11.10 +/- 5.54
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **TD3** Agent playing **FetchPickAndPlaceDense-v2**
|
25 |
+
This is a trained model of a **TD3** agent playing **FetchPickAndPlaceDense-v2**
|
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 |
+
```
|
config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "stable_baselines3.td3.policies", "__doc__": "\n Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\n\n :param observation_space: Observation space\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 features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\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 :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ", "__init__": "<function MultiInputPolicy.__init__ at 0x7af504baf2e0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7af504bba6c0>"}, "verbose": 0, "policy_kwargs": {"net_arch": [512, 512, 512]}, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 0.0, "learning_rate": 0.001, "tensorboard_log": null, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": false, "sde_sample_freq": -1, "_current_progress_remaining": 1.0, "_stats_window_size": 100, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "observation_space": {":type:": "<class 'gymnasium.spaces.dict.Dict'>", ":serialized:": "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", "spaces": "OrderedDict([('achieved_goal', Box(-inf, inf, (3,), float64)), ('desired_goal', Box(-inf, inf, (3,), float64)), ('observation', Box(-inf, inf, (25,), float64))])", "_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 True]", "bounded_above": "[ True True True True]", "_shape": [4], "low": "[-1. -1. -1. -1.]", "high": "[1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": "Generator(PCG64)"}, "n_envs": 1, "buffer_size": 1000000, "batch_size": 256, "learning_starts": 100, "tau": 0.005, "gamma": 0.99, "gradient_steps": 1, "optimize_memory_usage": false, "replay_buffer_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=", "__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], 'next_observations': typing.Dict[str, numpy.ndarray]}", "__doc__": "\n Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n Extends the ReplayBuffer to use dictionary observations\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 n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ", "__init__": "<function DictReplayBuffer.__init__ at 0x7af56869f0a0>", "add": "<function DictReplayBuffer.add at 0x7af56869f130>", "sample": "<function DictReplayBuffer.sample at 0x7af56869f1c0>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x7af56869f250>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7af5686a94c0>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "policy_delay": 2, "target_noise_clip": 0.5, "target_policy_noise": 0.2, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "actor_batch_norm_stats": [], "critic_batch_norm_stats": [], "actor_batch_norm_stats_target": [], "critic_batch_norm_stats_target": [], "system_info": {"OS": "Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024", "Python": "3.10.12", "Stable-Baselines3": "2.3.2", "PyTorch": "2.3.0+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 (472 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -11.104665819962975, "std_reward": 5.544368599225106, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-24T05:17:38.007589"}
|
td3-FetchPickAndPlaceDense-v2.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b74ca30d9714676cf1890af13a94212231851cd39299f14b59b8f4218d8a0c24
|
3 |
+
size 13090442
|
td3-FetchPickAndPlaceDense-v2/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.3.2
|
td3-FetchPickAndPlaceDense-v2/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f51440b3d0f6b08905f1bb6dcf429df0c058bf958a0385d77dd38b23e007cf8e
|
3 |
+
size 1120
|
td3-FetchPickAndPlaceDense-v2/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b39c7dab5a27f2e0fb2f3b5a4239743073f13dc302063aed5136a4d57f172ab
|
3 |
+
size 1120
|
td3-FetchPickAndPlaceDense-v2/data
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnRkMy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
|
5 |
+
"__module__": "stable_baselines3.td3.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for TD3 to be used with Dict observation spaces.\n\n :param observation_space: Observation space\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 features_extractor_class: Features extractor to use.\n :param features_extractor_kwargs: Keyword arguments\n to pass to the features extractor.\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 :param n_critics: Number of critic networks to create.\n :param share_features_extractor: Whether to share or not the features extractor\n between the actor and the critic (this saves computation time)\n ",
|
7 |
+
"__init__": "<function MultiInputPolicy.__init__ at 0x7af504baf2e0>",
|
8 |
+
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc._abc_data object at 0x7af504bba6c0>"
|
10 |
+
},
|
11 |
+
"verbose": 0,
|
12 |
+
"policy_kwargs": {
|
13 |
+
"net_arch": [
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512
|
17 |
+
]
|
18 |
+
},
|
19 |
+
"num_timesteps": 0,
|
20 |
+
"_total_timesteps": 0,
|
21 |
+
"_num_timesteps_at_start": 0,
|
22 |
+
"seed": null,
|
23 |
+
"action_noise": null,
|
24 |
+
"start_time": 0.0,
|
25 |
+
"learning_rate": 0.001,
|
26 |
+
"tensorboard_log": null,
|
27 |
+
"_last_obs": null,
|
28 |
+
"_last_episode_starts": null,
|
29 |
+
"_last_original_obs": null,
|
30 |
+
"_episode_num": 0,
|
31 |
+
"use_sde": false,
|
32 |
+
"sde_sample_freq": -1,
|
33 |
+
"_current_progress_remaining": 1.0,
|
34 |
+
"_stats_window_size": 100,
|
35 |
+
"ep_info_buffer": null,
|
36 |
+
"ep_success_buffer": null,
|
37 |
+
"_n_updates": 0,
|
38 |
+
"observation_space": {
|
39 |
+
":type:": "<class 'gymnasium.spaces.dict.Dict'>",
|
40 |
+
":serialized:": "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",
|
41 |
+
"spaces": "OrderedDict([('achieved_goal', Box(-inf, inf, (3,), float64)), ('desired_goal', Box(-inf, inf, (3,), float64)), ('observation', Box(-inf, inf, (25,), float64))])",
|
42 |
+
"_shape": null,
|
43 |
+
"dtype": null,
|
44 |
+
"_np_random": null
|
45 |
+
},
|
46 |
+
"action_space": {
|
47 |
+
":type:": "<class 'gymnasium.spaces.box.Box'>",
|
48 |
+
":serialized:": "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",
|
49 |
+
"dtype": "float32",
|
50 |
+
"bounded_below": "[ True True True True]",
|
51 |
+
"bounded_above": "[ True True True True]",
|
52 |
+
"_shape": [
|
53 |
+
4
|
54 |
+
],
|
55 |
+
"low": "[-1. -1. -1. -1.]",
|
56 |
+
"high": "[1. 1. 1. 1.]",
|
57 |
+
"low_repr": "-1.0",
|
58 |
+
"high_repr": "1.0",
|
59 |
+
"_np_random": "Generator(PCG64)"
|
60 |
+
},
|
61 |
+
"n_envs": 1,
|
62 |
+
"buffer_size": 1000000,
|
63 |
+
"batch_size": 256,
|
64 |
+
"learning_starts": 100,
|
65 |
+
"tau": 0.005,
|
66 |
+
"gamma": 0.99,
|
67 |
+
"gradient_steps": 1,
|
68 |
+
"optimize_memory_usage": false,
|
69 |
+
"replay_buffer_class": {
|
70 |
+
":type:": "<class 'abc.ABCMeta'>",
|
71 |
+
":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=",
|
72 |
+
"__module__": "stable_baselines3.common.buffers",
|
73 |
+
"__annotations__": "{'observation_space': <class 'gymnasium.spaces.dict.Dict'>, 'obs_shape': typing.Dict[str, typing.Tuple[int, ...]], 'observations': typing.Dict[str, numpy.ndarray], 'next_observations': typing.Dict[str, numpy.ndarray]}",
|
74 |
+
"__doc__": "\n Dict Replay buffer used in off-policy algorithms like SAC/TD3.\n Extends the ReplayBuffer to use dictionary observations\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 n_envs: Number of parallel environments\n :param optimize_memory_usage: Enable a memory efficient variant\n Disabled for now (see https://github.com/DLR-RM/stable-baselines3/pull/243#discussion_r531535702)\n :param handle_timeout_termination: Handle timeout termination (due to timelimit)\n separately and treat the task as infinite horizon task.\n https://github.com/DLR-RM/stable-baselines3/issues/284\n ",
|
75 |
+
"__init__": "<function DictReplayBuffer.__init__ at 0x7af56869f0a0>",
|
76 |
+
"add": "<function DictReplayBuffer.add at 0x7af56869f130>",
|
77 |
+
"sample": "<function DictReplayBuffer.sample at 0x7af56869f1c0>",
|
78 |
+
"_get_samples": "<function DictReplayBuffer._get_samples at 0x7af56869f250>",
|
79 |
+
"__abstractmethods__": "frozenset()",
|
80 |
+
"_abc_impl": "<_abc._abc_data object at 0x7af5686a94c0>"
|
81 |
+
},
|
82 |
+
"replay_buffer_kwargs": {},
|
83 |
+
"train_freq": {
|
84 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
85 |
+
":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
86 |
+
},
|
87 |
+
"use_sde_at_warmup": false,
|
88 |
+
"policy_delay": 2,
|
89 |
+
"target_noise_clip": 0.5,
|
90 |
+
"target_policy_noise": 0.2,
|
91 |
+
"lr_schedule": {
|
92 |
+
":type:": "<class 'function'>",
|
93 |
+
":serialized:": "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"
|
94 |
+
},
|
95 |
+
"actor_batch_norm_stats": [],
|
96 |
+
"critic_batch_norm_stats": [],
|
97 |
+
"actor_batch_norm_stats_target": [],
|
98 |
+
"critic_batch_norm_stats_target": []
|
99 |
+
}
|
td3-FetchPickAndPlaceDense-v2/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e96f9d044a28ebda589567de785a588b66aa1ab4df24cb6dc63289ad8c3f16b1
|
3 |
+
size 13076166
|
td3-FetchPickAndPlaceDense-v2/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c35cea3b2e60fb5e7e162d3592df775cd400e575a31c72f359fb9e654ab00c5
|
3 |
+
size 864
|
td3-FetchPickAndPlaceDense-v2/system_info.txt
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-6.1.85+-x86_64-with-glibc2.35 # 1 SMP PREEMPT_DYNAMIC Sun Apr 28 14:29:16 UTC 2024
|
2 |
+
- Python: 3.10.12
|
3 |
+
- Stable-Baselines3: 2.3.2
|
4 |
+
- PyTorch: 2.3.0+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
|