Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Models (LLMs). Recent studies suggest that RLVR can elicit strong mathematical reasoning in LLMs through two seemingly paradoxical mechanisms: spurious rewards, which suppress exploitation by rewarding outcomes unrelated to the ground truth, and entropy minimization, which suppresses exploration by pushing the model toward more confident and deterministic outputs, highlighting a puzzling dynamic: both discouraging exploitation and discouraging exploration improve reasoning performance, yet the underlying principles that reconcile these effects remain poorly understood. We focus on two fundamental questions: (i) how policy entropy relates to performance, and (ii) whether spurious rewards yield gains, potentially through the interplay of clipping bias and model contamination. Our results show that clipping bias under spurious rewards reduces policy entropy, leading to more confident and deterministic outputs, while entropy minimization alone is insufficient for improvement. We further propose a reward-misalignment model explaining why spurious rewards can enhance performance beyond contaminated settings. Our findings clarify the mechanisms behind spurious-reward benefits and provide principles for more effective RLVR training.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningMathematical ReasoningSimilar Papers 제목 키워드 기반
A Unified Framework for Rethinking Policy Divergence Measures in GRPO
Reinforcement Learning with Verified Reward (RLVR) has emerged as a critical paradigm for advancing the reasoning capabilities of Large Language Models (LLMs). Most existing RLVR methods, such as GRPO and its variants, e…
Reinforcement LearningMathematical ReasoningClip-Low Increases Entropy and Clip-High Decreases Entropy in Reinforcement Learning of Large Language Models
Reinforcement learning with verifiable rewards (RLVR) has recently emerged as the leading approach for enhancing the reasoning capabilities of large language models (LLMs). However, RLVR is prone to entropy collapse, whe…
Reinforcement LearningDemystifying On-Policy Distillation: Roles, Pathologies, and Regulations
On-policy distillation (OPD) has become a key paradigm in LLM post-training, yet its training dynamics remain poorly understood. We present a systematic study examining the role, pathologies, and regulations of OPD. We f…
Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models
Reinforcement learning with verifiable rewards (RLVR), which typically adopts Pass@1 as the reward, has faced the issues in balancing exploration and exploitation, causing policies to prefer conservative actions, converg…
Reinforcement LearningSemantic-Space Exploration and Exploitation in RLVR for LLM Reasoning
Reinforcement Learning with Verifiable Rewards (RLVR) for LLM reasoning is often framed as balancing exploration and exploitation in action space, typically operationalized with token-level proxies (e.g., output entropy …
Reinforcement Learning