Tag: Proximal Policy Optimization
Browse our exclusive articles!
Self-Guide: Enhancing Language Agents with Internal Rewards
Discover how Self-Guide boosts language agents by co-evolving policy and internal rewards for improved learning and inference performance.
Preventing Reward Hacking in RLHF with Sign-Certified PO
Discover how Sign-Certified Policy Optimization improves RLHF by mitigating reward hacking through advantage sign robustness for better AI alignment.
Chart-RL: Reinforcement Learning for Better Chart QA
Discover Chart-RL, a reinforcement learning framework enhancing visual reasoning in chart question answering with efficient policy optimization.
Multi-Turn RL for Tool-Calling Agents with Reward Calibration
Enhance tool-calling agents using multi-turn reinforcement learning and iterative reward calibration for superior performance in customer service tasks.
Polychromic Objectives Boost Reinforcement Learning Diversity
Enhance reinforcement learning with polychromic objectives that improve exploration, diversity, and generalization in pretrained policies.