Owner
opendilab
2 indexed repositories · View on GitHub
-
LightZero
[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)
Python · 1647 stars
-
LightRFT
LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework
Python · 404 stars
-
Difficulty 4/5 3-5 days Newbie friendliness 52/100
-
Gumbel AlphaZero (ctree) does not learn: OOB child indexing, frozen noise, and algorithm deviations Open
Difficulty 5/5 Over a week Newbie friendliness 45/100
-
Difficulty 4/5 3-5 days Newbie friendliness 48/100
-
EfficientZero v2 Openalgorithm
Difficulty 5/5 Over a week Newbie friendliness 25/100
-
discussion
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 55/100
-
config dependencies
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
bug documentation enhancement polish refactor style
Difficulty 5/5 Over a week Newbie friendliness 20/100
-
可能的性能优化: Openefficiency optimization
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
bug
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
关于项目的疑问 Opendiscussion efficiency optimization
Difficulty 5/5 Over a week Newbie friendliness 20/100
-
bug
Difficulty 3/5 1-2 days Newbie friendliness 30/100