Arbitrary Entropy Policy Optimization: Entropy Is Controllable in Reinforcement Fine-tuning
Paper
•
2510.08141
•
Published
•
1
Chen Wang
wc597358816
AI & ML interests
None yet
Recent Activity
authored
a paper
5 days ago
Arbitrary Entropy Policy Optimization: Entropy Is Controllable in
Reinforcement Fine-tuning
authored
a paper
5 days ago
Distribution-Centric Policy Optimization Dominates Exploration-Exploitation Trade-off
updated
a model
5 days ago
wc597358816/DCPO_Qwen3-4B
Organizations
None yet
authored
2
papers
5 days ago