Low-probability Tokens Sustain Exploration in Reinforcement Learning with Verifiable Reward
Paper
•
2510.03222
•
Published
•
75
Jae-moon Yoon
ZVmoon
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 2 months ago
Low-probability Tokens Sustain Exploration in Reinforcement Learning
with Verifiable Reward
upvoted
a
paper
about 2 months ago
Rethinking Entropy Regularization in Large Reasoning Models
upvoted
a
paper
about 2 months ago
Harnessing Uncertainty: Entropy-Modulated Policy Gradients for
Long-Horizon LLM Agents
Organizations
None yet
upvoted
3
papers
about 2 months ago
liked
a
model
about 2 months ago
