-
Notifications
You must be signed in to change notification settings - Fork 168
Pull requests: opendilab/LightZero
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feature(xjy): adaptively set the config of batchsize and accumulation_steps
#410
opened Aug 27, 2025 by
xiongjyu
Loading…
fix(tj): 增加专家冲突矩阵 和 指标
enhancement
New feature or request
research
Research work in progress
#406
opened Aug 19, 2025 by
tAnGjIa520
Loading…
fix(xjy): adding the messenger environment
environment
New or improved environment
research
Research work in progress
#405
opened Aug 18, 2025 by
xiongjyu
Loading…
fix(pu): fix longrun performance of muzero in mspacman and qbert
bug
Something isn't working
config
New or improved configuration
#400
opened Aug 12, 2025 by
puyuan1996
Loading…
WIP: polish(pu): add a polished version of qwen prior policy
#397
opened Aug 11, 2025 by
puyuan1996
Loading…
WIP: feature(nyz/pu): add init version of async demo using task pipeline
#396
opened Aug 5, 2025 by
puyuan1996
Loading…
WIP: feature(pu): add init version of async unizero using multi-threading
#395
opened Aug 1, 2025 by
puyuan1996
Loading…
feature(tj): add experiments to test the gradient conflicts from MOE module
enhancement
New feature or request
#390
opened Jul 24, 2025 by
tAnGjIa520
Loading…
feature(xjy): add multi-task learning pipeline in jericho environment
config
New or improved configuration
enhancement
New feature or request
#365
opened May 27, 2025 by
xiongjyu
Loading…
fix(pu): fix chess reset bug when use alphazero ctree
#364
opened May 23, 2025 by
puyuan1996
Loading…
WIP: feature(pu): add unizero multitask balance pipeline
#356
opened Apr 29, 2025 by
puyuan1996
Loading…
WIP: feature(pu): add unizero/muzero multitask pipeline and net plasticity related metrics
#353
opened Apr 25, 2025 by
puyuan1996
Loading…
How to fix the bug of loading trained model for evaluation
#340
opened Apr 2, 2025 by
xiongjyu
Loading…
feature(xjy): add mamba2 as a unizero backbone option
algorithm
New algorithm
#338
opened Mar 31, 2025 by
xiongjyu
Loading…
WIP: feature(pu): add muzero with history encoder
algorithm
New algorithm
enhancement
New feature or request
#334
opened Mar 21, 2025 by
puyuan1996
Loading…
feature(khev): add equation solver env and related configs
enhancement
New feature or request
environment
New or improved environment
#331
opened Mar 17, 2025 by
Khev
Loading…
WIP: feature(whl): add decoder regularization
enhancement
New feature or request
#326
opened Feb 21, 2025 by
kxzxvbk
Loading…
WIP: feature(pu): add sampled_unizero multitask pipeline
enhancement
New feature or request
research
Research work in progress
#311
opened Dec 24, 2024 by
puyuan1996
Loading…
WIP: feature(whl): add pretrained llm for unizero
research
Research work in progress
#310
opened Dec 24, 2024 by
kxzxvbk
Loading…
feature(pu): unizero and muzero multitask ddp pipeline
config
New or improved configuration
efficiency optimization
Efficiency optimization (time, memory and so on)
enhancement
New feature or request
research
Research work in progress
#300
opened Nov 29, 2024 by
puyuan1996
Loading…
feature(pu): add seller env, self-judge pipeline and mcts/alphazero config
algorithm
New algorithm
config
New or improved configuration
environment
New or improved environment
#276
opened Sep 19, 2024 by
puyuan1996
Loading…
Requesting Guidance on training and testing in a tetris environment. #265
environment
New or improved environment
#267
opened Aug 17, 2024 by
lunathanael
Loading…
Previous Next
ProTip!
Adding no:label will show everything without a label.