-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Issues: thu-ml/tianshou
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
Use Altair inside a notebook to display benchmark results
documentation
good first issue
Good for newcomers
#1136
opened May 4, 2024 by
MischaPanch
how to run RL using multi-nodes in cluster
documentation
question
Further information is requested
#1133
opened May 2, 2024 by
HYB777
Adjust locations of setting the policy in train/eval mode
bug
Something isn't working
refactoring
No change to functionality
#1122
opened Apr 24, 2024 by
maxhuettenrauch
Provide a devcontainer, base GH actions off it
build/test
minor
Requires small changes to be fixed
#1118
opened Apr 17, 2024 by
MischaPanch
Should we use the new schedule-free optimizer?
optimization
Performance optimization (throughout, memory, processing speed)
#1115
opened Apr 15, 2024 by
MischaPanch
Should we use torch.compile?
optimization
Performance optimization (throughout, memory, processing speed)
#1114
opened Apr 15, 2024 by
MischaPanch
Revisit "warm-up" phase in examples
algorithm enhancement
Not quite a new algorithm, but an enhancement to algo. functionality
#1112
opened Apr 14, 2024 by
MischaPanch
Use Atari-5 for future benchmarking of discrete RL
build/test
discussion
Discussion of a typical issue
#1110
opened Apr 12, 2024 by
nuance1979
4 of 9 tasks
Don't pass envpool envs where vectorenvs are needed
bug
Something isn't working
good first issue
Good for newcomers
refactoring
No change to functionality
#1096
opened Apr 3, 2024 by
MischaPanch
Re-examine the whole state story for RNNs
refactoring
No change to functionality
RNN
Temporary label to group all things RNN
tentative
Up to discussion, may be dismissed
#1095
opened Apr 3, 2024 by
MischaPanch
Re-examine the need of utils.net.common.DataParallelNet
refactoring
No change to functionality
tentative
Up to discussion, may be dismissed
#1094
opened Apr 3, 2024 by
MischaPanch
Reduce duplication between examples/atari/atari_network and examples/vizdoom/network
good first issue
Good for newcomers
refactoring
No change to functionality
#1092
opened Apr 3, 2024 by
MischaPanch
Better interfaces and names for Actor, Critic, Net and other classes
refactoring
No change to functionality
#1091
opened Apr 3, 2024 by
MischaPanch
Buffer: fix discrepancy in slicing order
Batch and Buffer
Improvements in internal data structures, temporary label
breaking changes
Changes in public interfaces. Includes small changes or changes in keys
refactoring
No change to functionality
#1090
opened Apr 3, 2024 by
MischaPanch
Batch: don't just strip off empty entries when creating batches
Batch and Buffer
Improvements in internal data structures, temporary label
bug
Something isn't working
#1089
opened Apr 3, 2024 by
MischaPanch
Batch: don't just set 0 when elements have None entries
Batch and Buffer
Improvements in internal data structures, temporary label
bug
Something isn't working
#1088
opened Apr 3, 2024 by
MischaPanch
Batch: only allow entries with the same length
Batch and Buffer
Improvements in internal data structures, temporary label
breaking changes
Changes in public interfaces. Includes small changes or changes in keys
refactoring
No change to functionality
#1087
opened Apr 3, 2024 by
MischaPanch
Batch: deprecate setattr
Batch and Buffer
Improvements in internal data structures, temporary label
breaking changes
Changes in public interfaces. Includes small changes or changes in keys
refactoring
No change to functionality
#1085
opened Apr 3, 2024 by
MischaPanch
How to monitor the episode/epoch return/length in Tianshou?
question
Further information is requested
#1082
opened Mar 30, 2024 by
PingH129
1 of 6 tasks
Typing annotations of step from MyTestEnv is incompatible with its current subclass gym.Env because it can generate non-scalar rewards.
build/test
typing
Mainly improving types, no or very few functional changes
#1080
opened Mar 23, 2024 by
dantp-ai
4 of 7 tasks
Revisit and maybe optimize Collectors
optimization
Performance optimization (throughout, memory, processing speed)
tentative
Up to discussion, may be dismissed
Support Dict observation spaces
documentation
enhancement
Feature that is not a new algorithm or an algorithm enhancement
good first issue
Good for newcomers
tentative
Up to discussion, may be dismissed
#1065
opened Feb 26, 2024 by
MischaPanch
Code duplication between ReplayBuffer and ReplayBufferManager
good first issue
Good for newcomers
refactoring
No change to functionality
#1057
opened Feb 16, 2024 by
bordeauxred
Improve and extend Documentation Content
documentation
good first issue
Good for newcomers
#1056
opened Feb 15, 2024 by
MischaPanch
12 tasks
ProTip!
Type g i on any issue or pull request to go back to the issue listing page.