Initial commit
Browse files- README.md +37 -0
- SAC-PandaReachDense-v3.zip +3 -0
- SAC-PandaReachDense-v3/_stable_baselines3_version +1 -0
- SAC-PandaReachDense-v3/actor.optimizer.pth +3 -0
- SAC-PandaReachDense-v3/critic.optimizer.pth +3 -0
- SAC-PandaReachDense-v3/data +114 -0
- SAC-PandaReachDense-v3/ent_coef_optimizer.pth +3 -0
- SAC-PandaReachDense-v3/policy.pth +3 -0
- SAC-PandaReachDense-v3/pytorch_variables.pth +3 -0
- SAC-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: SAC
|
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: -0.26 +/- 0.10
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **SAC** Agent playing **PandaReachDense-v3**
|
25 |
+
This is a trained model of a **SAC** 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 |
+
```
|
SAC-PandaReachDense-v3.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f158c8f131ba3e6ffcd13e3a1579cf18891d8de9d55af8e51e7f271c33a0ff49
|
3 |
+
size 3141747
|
SAC-PandaReachDense-v3/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
2.3.2
|
SAC-PandaReachDense-v3/actor.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7d7cffdee80fce2580fa1b12001cc5223f28e2f2adb49838d9be740dfade439
|
3 |
+
size 571982
|
SAC-PandaReachDense-v3/critic.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c96c6ce7d3948fae28ff8b178aa81b8107c8f38dcba9e2aa471c5a1acb1471df
|
3 |
+
size 1131946
|
SAC-PandaReachDense-v3/data
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"policy_class": {
|
3 |
+
":type:": "<class 'abc.ABCMeta'>",
|
4 |
+
":serialized:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu",
|
5 |
+
"__module__": "stable_baselines3.sac.policies",
|
6 |
+
"__doc__": "\n Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\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 0x7c957102f7f0>",
|
8 |
+
"__abstractmethods__": "frozenset()",
|
9 |
+
"_abc_impl": "<_abc._abc_data object at 0x7c957103e6c0>"
|
10 |
+
},
|
11 |
+
"verbose": 1,
|
12 |
+
"policy_kwargs": {
|
13 |
+
"use_sde": false
|
14 |
+
},
|
15 |
+
"num_timesteps": 1000000,
|
16 |
+
"_total_timesteps": 1000000,
|
17 |
+
"_num_timesteps_at_start": 0,
|
18 |
+
"seed": null,
|
19 |
+
"action_noise": null,
|
20 |
+
"start_time": 1717260567748910776,
|
21 |
+
"learning_rate": 0.01,
|
22 |
+
"tensorboard_log": null,
|
23 |
+
"_last_obs": {
|
24 |
+
":type:": "<class 'collections.OrderedDict'>",
|
25 |
+
":serialized:": "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",
|
26 |
+
"achieved_goal": "[[ 0.3023255 -0.01341968 0.46535262]\n [ 0.3023255 -0.01341968 0.46535262]\n [ 0.3023255 -0.01341968 0.46535262]\n [-1.9884398 -0.14644921 1.6493461 ]]",
|
27 |
+
"desired_goal": "[[ 0.89085454 -1.5616426 -1.3101369 ]\n [ 0.7735291 -0.7645848 0.924458 ]\n [ 0.964734 -0.622809 0.54673904]\n [-0.5275317 -0.3090982 1.6461825 ]]",
|
28 |
+
"observation": "[[ 0.3023255 -0.01341968 0.46535262 0.54474574 -0.01308281 0.38217503]\n [ 0.3023255 -0.01341968 0.46535262 0.54474574 -0.01308281 0.38217503]\n [ 0.3023255 -0.01341968 0.46535262 0.54474574 -0.01308281 0.38217503]\n [-1.9884398 -0.14644921 1.6493461 0.35414076 -1.5085231 1.7430289 ]]"
|
29 |
+
},
|
30 |
+
"_last_episode_starts": {
|
31 |
+
":type:": "<class 'numpy.ndarray'>",
|
32 |
+
":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
|
33 |
+
},
|
34 |
+
"_last_original_obs": {
|
35 |
+
":type:": "<class 'collections.OrderedDict'>",
|
36 |
+
":serialized:": "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",
|
37 |
+
"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 [-7.0365869e-02 -6.0319649e-03 2.4798883e-01]]",
|
38 |
+
"desired_goal": "[[ 0.07442327 -0.14033225 0.02231891]\n [ 0.06361905 -0.06793272 0.22584173]\n [ 0.08122665 -0.05505474 0.19143978]\n [-0.05619257 -0.0265593 0.29157507]]",
|
39 |
+
"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 [-7.0365869e-02 -6.0319649e-03 2.4798883e-01 -7.2805837e-02\n -9.3219119e-01 8.8050139e-01]]"
|
40 |
+
},
|
41 |
+
"_episode_num": 332305,
|
42 |
+
"use_sde": false,
|
43 |
+
"sde_sample_freq": -1,
|
44 |
+
"_current_progress_remaining": 0.0,
|
45 |
+
"_stats_window_size": 100,
|
46 |
+
"ep_info_buffer": {
|
47 |
+
":type:": "<class 'collections.deque'>",
|
48 |
+
":serialized:": "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"
|
49 |
+
},
|
50 |
+
"ep_success_buffer": {
|
51 |
+
":type:": "<class 'collections.deque'>",
|
52 |
+
":serialized:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="
|
53 |
+
},
|
54 |
+
"_n_updates": 249975,
|
55 |
+
"buffer_size": 1000000,
|
56 |
+
"batch_size": 256,
|
57 |
+
"learning_starts": 100,
|
58 |
+
"tau": 0.005,
|
59 |
+
"gamma": 0.99,
|
60 |
+
"gradient_steps": 1,
|
61 |
+
"optimize_memory_usage": false,
|
62 |
+
"replay_buffer_class": {
|
63 |
+
":type:": "<class 'abc.ABCMeta'>",
|
64 |
+
":serialized:": "gAWVOQAAAAAAAACMIHN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5idWZmZXJzlIwQRGljdFJlcGxheUJ1ZmZlcpSTlC4=",
|
65 |
+
"__module__": "stable_baselines3.common.buffers",
|
66 |
+
"__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]}",
|
67 |
+
"__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 ",
|
68 |
+
"__init__": "<function DictReplayBuffer.__init__ at 0x7c957114f6d0>",
|
69 |
+
"add": "<function DictReplayBuffer.add at 0x7c957114f760>",
|
70 |
+
"sample": "<function DictReplayBuffer.sample at 0x7c957114f7f0>",
|
71 |
+
"_get_samples": "<function DictReplayBuffer._get_samples at 0x7c957114f880>",
|
72 |
+
"__abstractmethods__": "frozenset()",
|
73 |
+
"_abc_impl": "<_abc._abc_data object at 0x7c9571152c00>"
|
74 |
+
},
|
75 |
+
"replay_buffer_kwargs": {},
|
76 |
+
"train_freq": {
|
77 |
+
":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>",
|
78 |
+
":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"
|
79 |
+
},
|
80 |
+
"use_sde_at_warmup": false,
|
81 |
+
"target_entropy": -3.0,
|
82 |
+
"ent_coef": "auto",
|
83 |
+
"target_update_interval": 1,
|
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": "Generator(PCG64)"
|
106 |
+
},
|
107 |
+
"n_envs": 4,
|
108 |
+
"lr_schedule": {
|
109 |
+
":type:": "<class 'function'>",
|
110 |
+
":serialized:": "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"
|
111 |
+
},
|
112 |
+
"batch_norm_stats": [],
|
113 |
+
"batch_norm_stats_target": []
|
114 |
+
}
|
SAC-PandaReachDense-v3/ent_coef_optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:499ec6432f190a93d1e64a4a730f3ef1849f53bd6c6b410edf3ac9524b82dd26
|
3 |
+
size 1940
|
SAC-PandaReachDense-v3/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c01395909786a03a723ee0693bd3b5e4d76eba9efad818aed4bb93e8d5d9861
|
3 |
+
size 1416630
|
SAC-PandaReachDense-v3/pytorch_variables.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f7ad8933f3fb33663a83414e15e64afc83215df8648fbed5c86754170978a21
|
3 |
+
size 1180
|
SAC-PandaReachDense-v3/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: False
|
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:": "gAWVNwAAAAAAAACMHnN0YWJsZV9iYXNlbGluZXMzLnNhYy5wb2xpY2llc5SMEE11bHRpSW5wdXRQb2xpY3mUk5Qu", "__module__": "stable_baselines3.sac.policies", "__doc__": "\n Policy class (with both actor and critic) for SAC.\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 use_sde: Whether to use State Dependent Exploration or not\n :param log_std_init: Initial value for the log standard deviation\n :param use_expln: Use ``expln()`` function instead of ``exp()`` when using gSDE 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 clip_mean: Clip the mean output when using gSDE to avoid numerical instability.\n :param features_extractor_class: Features extractor to use.\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 0x7c957102f7f0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c957103e6c0>"}, "verbose": 1, "policy_kwargs": {"use_sde": false}, "num_timesteps": 1000000, "_total_timesteps": 1000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1717260567748910776, "learning_rate": 0.01, "tensorboard_log": null, "_last_obs": {":type:": "<class 'collections.OrderedDict'>", ":serialized:": "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", "achieved_goal": "[[ 0.3023255 -0.01341968 0.46535262]\n [ 0.3023255 -0.01341968 0.46535262]\n [ 0.3023255 -0.01341968 0.46535262]\n [-1.9884398 -0.14644921 1.6493461 ]]", "desired_goal": "[[ 0.89085454 -1.5616426 -1.3101369 ]\n [ 0.7735291 -0.7645848 0.924458 ]\n [ 0.964734 -0.622809 0.54673904]\n [-0.5275317 -0.3090982 1.6461825 ]]", "observation": "[[ 0.3023255 -0.01341968 0.46535262 0.54474574 -0.01308281 0.38217503]\n [ 0.3023255 -0.01341968 0.46535262 0.54474574 -0.01308281 0.38217503]\n [ 0.3023255 -0.01341968 0.46535262 0.54474574 -0.01308281 0.38217503]\n [-1.9884398 -0.14644921 1.6493461 0.35414076 -1.5085231 1.7430289 ]]"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAEBAQGUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////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 [-7.0365869e-02 -6.0319649e-03 2.4798883e-01]]", "desired_goal": "[[ 0.07442327 -0.14033225 0.02231891]\n [ 0.06361905 -0.06793272 0.22584173]\n [ 0.08122665 -0.05505474 0.19143978]\n [-0.05619257 -0.0265593 0.29157507]]", "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 [-7.0365869e-02 -6.0319649e-03 2.4798883e-01 -7.2805837e-02\n -9.3219119e-01 8.8050139e-01]]"}, "_episode_num": 332305, "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:": "gAWVhgAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKUKIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIiIhlLg=="}, "_n_updates": 249975, "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 0x7c957114f6d0>", "add": "<function DictReplayBuffer.add at 0x7c957114f760>", "sample": "<function DictReplayBuffer.sample at 0x7c957114f7f0>", "_get_samples": "<function DictReplayBuffer._get_samples at 0x7c957114f880>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc._abc_data object at 0x7c9571152c00>"}, "replay_buffer_kwargs": {}, "train_freq": {":type:": "<class 'stable_baselines3.common.type_aliases.TrainFreq'>", ":serialized:": "gAWVYQAAAAAAAACMJXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi50eXBlX2FsaWFzZXOUjAlUcmFpbkZyZXGUk5RLAWgAjBJUcmFpbkZyZXF1ZW5jeVVuaXSUk5SMBHN0ZXCUhZRSlIaUgZQu"}, "use_sde_at_warmup": false, "target_entropy": -3.0, "ent_coef": "auto", "target_update_interval": 1, "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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"}, "batch_norm_stats": [], "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": "False", "Numpy": "1.25.2", "Cloudpickle": "2.2.1", "Gymnasium": "0.29.1", "OpenAI Gym": "0.25.2"}}
|
replay.mp4
ADDED
Binary file (691 kB). View file
|
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": -0.2553447760641575, "std_reward": 0.1028342594802608, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-06-01T22:53:24.564987"}
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99bbf3cced4f3eec730a93996e41b54f48275049b33a537dc270c7e028ec98d4
|
3 |
+
size 2847
|