Skip to content

Issues: thu-ml/tianshou

Towards Roadmap
#1215 opened Sep 8, 2024 by MischaPanch
Open 11
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

136 Open 610 Closed
136 Open 610 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Major Performance Decrease in Tianshou 1.2 Compared to 0.5 on Windows and Linux
#1225 opened Oct 30, 2024 by ULudo
5 of 9 tasks
5
next_dist of function _target_dist in c51.py maybe not correctly calculated.
#1223 opened Oct 22, 2024 by musicaudience
Wandb logger
#1222 opened Oct 14, 2024 by dev0Guy
6 tasks
1
Question on benchmark hyperparameters
#1220 opened Oct 9, 2024 by RolandStolz
5 of 9 tasks
1
AttributeError: 'dict' object has no attribute 'terminated' with multi agent env having gymnasium.spaces.Dict observation space
#1219 opened Oct 7, 2024 by fortminors
5 of 9 tasks
No response after setting render
#1217 opened Sep 21, 2024 by zdx3578
9 tasks
Question about Actor's outputs and selected actions
#1216 opened Sep 19, 2024 by flammmes
4 of 5 tasks
Towards Roadmap major Large changes that cannot or should not be broken down into smaller ones
#1215 opened Sep 8, 2024 by MischaPanch Release 2.0.0
@opcode81 @MischaPanch
11
Support custom scores for Trainer in high-level interfaces high-level-api Mainly affects tianshou.highlevel
#1205 opened Aug 14, 2024 by MischaPanch Release 2.0.0
Refactoring: make Trainer more flexible refactoring No change to functionality
#1204 opened Aug 14, 2024 by MischaPanch Release 2.0.0
Handling LR scheduling when episodes instead of steps are collected algorithm enhancement Not quite a new algorithm, but an enhancement to algo. functionality
#1198 opened Aug 10, 2024 by MischaPanch
Learning rate scheduler confusion documentation enhancement Feature that is not a new algorithm or an algorithm enhancement
#1197 opened Aug 9, 2024 by opcode81
1
Suggestion - Redesign RayEnvWorker for Improved Performance performance issues Slow execution or poor-quality results
#1172 opened Jul 10, 2024 by destin-v
4 tasks done
@destin-v
14
MPO Implementation new algorithm Adding a new RL algorithm
#1165 opened Jul 4, 2024 by ziqiao30 Release 2.0.0
1
Documentation for multi-agent needs fixing bug Something isn't working MARL Temporary label to group all things MARL
#1163 opened Jun 21, 2024 by destin-v
5 of 9 tasks
1
will add dreamerv3 ? new algorithm Adding a new RL algorithm
#1160 opened Jun 8, 2024 by zdx3578
1 of 9 tasks
Release 2.0.0
1
Clarification Needed on Implementing Action Masking in DQN with preprocess_fn in Collector question Further information is requested
#1159 opened Jun 7, 2024 by NeoBerekov
1
expected to be in range of [-1, 0], but got 1 not reproduced yet Not yet tested or reproduced by a reviewer
#1156 opened May 31, 2024 by WillInvest
4
How to save the log which axis is each epoch not epoch's steps? enhancement Feature that is not a new algorithm or an algorithm enhancement
#1154 opened May 28, 2024 by hems111318136
9 tasks
2
Support dict observation spaces in highlevel api enhancement Feature that is not a new algorithm or an algorithm enhancement refactoring No change to functionality
#1152 opened May 24, 2024 by MischaPanch
@MischaPanch
Poetry update the torch versioned from cuda (2.0.1+cu118) to cpu (2.1.1) defaultly on Windows build/test
#1145 opened May 11, 2024 by coolermzb3
6 of 9 tasks
9
Document effects of the relations between buffer size, num workers and episode length documentation
#1143 opened May 10, 2024 by MischaPanch
@MischaPanch
How can I make action sampling within the range specified by my environment when using onpolicy_trainer? question Further information is requested
#1142 opened May 9, 2024 by lidaken
6
Extend benchmark with mujoco v4 envs documentation experiment-eval Issues about evaluation: plots, stats, multiprocessing etc.
#1140 opened May 6, 2024 by MischaPanch
Does Tianshou truly supports MARL out of the box? MARL Temporary label to group all things MARL question Further information is requested
#1137 opened May 5, 2024 by Legendorik
4 of 9 tasks
1
ProTip! Follow long discussions with comments:>50.