thu-ml tianshou issues - Githubissues

thu-ml / tianshou

An elegant PyTorch deep reinforcement learning library.

https://tianshou.org

MIT License

7.48k stars 1.09k forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

ModuleNotFoundError: No module named 'tianshou.highlevel'

#1149 luweiagi opened 3 days ago
2
ImportError: cannot import name 'Self' from 'typing' (/root/miniconda3/lib/python3.10/typing.py)

#1148 luweiagi closed 3 days ago
1
[question] Why does Tianshou use a replay buffer in on-policy RL algorithms?

#1147 maguro27 closed 6 days ago
1
[Fix&Enhance&Format] On README.md about poetry install

#1146 coolermzb3 opened 1 week ago
0
Poetry update the torch versioned from cuda (2.0.1+cu118) to cpu (2.1.1) defaultly on Windows

#1145 coolermzb3 opened 1 week ago
5
Refactoring/remove is empty batch

#1144 dantp-ai opened 1 week ago
0
Document effects of the relations between buffer size, num workers and episode length

#1143 MischaPanch opened 1 week ago
0
How can I make action sampling within the range specified by my environment when using onpolicy_trainer?

#1142 lidaken opened 1 week ago
6
Bugfix/parallel launcher for linux

#1141 MischaPanch closed 1 week ago
0
Extend benchmark with mujoco v4 envs

#1140 MischaPanch opened 1 week ago
0
Bump jinja2 from 3.1.3 to 3.1.4

#1139 dependabot[bot] closed 1 week ago
0
Bump werkzeug from 3.0.1 to 3.0.3

#1138 dependabot[bot] closed 1 week ago
0
Does Tianshou truly supports MARL out of the box?

#1137 Legendorik opened 2 weeks ago
1
Use Altair inside a notebook to display benchmark results

#1136 MischaPanch opened 2 weeks ago
0
Potential confusion about where start timesteps are collected in HL interfaces

#1135 MischaPanch closed 2 weeks ago
4
Bump tqdm from 4.66.1 to 4.66.3

#1134 dependabot[bot] closed 2 weeks ago
1
how to run RL using multi-nodes in cluster

#1133 HYB777 opened 2 weeks ago
1
Add quotations to symbols in base policy docu.

#1132 bordeauxred closed 2 weeks ago
1
Improvements pertaining to the handling of multi-experiment creation

#1131 opcode81 closed 2 weeks ago
0
Improve the documentation of compute_episodic_return in base policy.

#1130 bordeauxred closed 2 weeks ago
0
Change log is chaotic and partly uninformative

#1129 opcode81 opened 2 weeks ago
2
Support Actor preprocessing network reuse for continuous case, fixes in DQN network

#1128 opcode81 closed 2 weeks ago
1
Feat/collect equal episode num in all envs

#1127 MischaPanch opened 2 weeks ago
0
Unified build method for HL experiment

#1126 maxhuettenrauch closed 2 weeks ago
2
batch - is_empty()

#1125 DarkTechPirate opened 3 weeks ago
7
Changelog + dependabot bumps

#1124 MischaPanch closed 3 weeks ago
5
Adjust locations of setting the policy in train/eval mode

#1123 maxhuettenrauch closed 1 week ago
4
Adjust locations of setting the policy in train/eval mode

#1122 maxhuettenrauch opened 3 weeks ago
1
Revisit `Launcher` for starting multiple experiments

#1121 MischaPanch closed 1 week ago
1
Glad you agree with me on this ^^. I'm not sure whether anywhere in the code the retrieval of the slice with empty values is used. For me it's fine to completely remove it, however, many tests will need to be adjusted, as now many of them rely on this somehow weird retrieval mechanism.

#1120 MischaPanch closed 4 weeks ago
0
Some issues regarding configuration parameters

#1119 yshichseu closed 2 weeks ago
5
Provide a devcontainer, base GH actions off it

#1118 MischaPanch opened 1 month ago
0
Add non in-place version of `Batch.to_torch`

#1117 dantp-ai closed 1 month ago
2
Add the non-in-place counterpart of `Batch.to_torch`

#1116 dantp-ai closed 1 month ago
0
Should we use the new schedule-free optimizer?

#1115 MischaPanch opened 1 month ago
1
Should we use torch.compile?

#1114 MischaPanch opened 1 month ago
2
Update README.md

#1113 sleeplessai closed 1 month ago
1
Revisit "warm-up" phase in examples

#1112 MischaPanch opened 1 month ago
0
UnboundLocalError: cannot access local variable 'obs_space_dtype' in atari_wrapper.py

#1111 zhuyuanyang closed 1 month ago
1
Use Atari-5 for future benchmarking of discrete RL

#1110 nuance1979 opened 1 month ago
1
Update batch.py

#1109 DarkTechPirate closed 1 month ago
0
Batch: remove `is_empty`

#1108 MischaPanch opened 1 month ago
24
Bump idna from 3.4 to 3.7

#1107 dependabot[bot] closed 3 weeks ago
2
Warn on batch.add when missing keys

#1106 maxhuettenrauch closed 1 week ago
4
Changed .keys() to get_keys() in batch class

#1105 arnaujc91 closed 1 month ago
1
/test/continuous/test_ppo.py TypeError on torch.distributions

#1104 nado5 closed 1 month ago
3
Fix/deterministic action space sampling

#1103 maxhuettenrauch closed 1 month ago
1
use explicit multiprocessing context for creating Pipe in subproc.py

#1102 maxhuettenrauch closed 1 month ago
3
AttributeError: 'PPOPolicy' object has no attribute 'set_eps'

#1101 prologua closed 1 month ago
2
Fix/reset before collect in procedural examples, tests and hl experiment

#1100 maxhuettenrauch closed 1 month ago
13