PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization

Abstract

Despite Proximal Policy Optimization (PPO) dominating policy gradient methods -- from robotic control to game AI -- its static trust region forces a brittle trade-off: aggressive clipping stifles early exploration, while late-stage updates destabilize convergence. PPO-BR establishes a new paradigm in adaptive RL by fusing exploration and convergence signals into a single bounded trust region -- a theoretically grounded innovation that outperforms five SOTA baselines with less than 2% overhead. This work bridges a critical gap in phase-aware learning, enabling real-world deployment in safety-critical systems like robotic surgery within a single adaptive mechanism. PPO-BR achieves 29.1% faster convergence by combining: (1) entropy-driven expansion (epsilon up) for exploration in high-uncertainty states, and (2) reward-guided contraction (epsilon down) for convergence stability. On six diverse benchmarks (MuJoCo, Atari, sparse-reward), PPO-BR achieves 29.1% faster convergence (p < 0.001), 2.3x lower reward variance than PPO, and less than 1.8% runtime overhead with only five lines of code change. PPO-BR's simplicity and theoretical guarantees make it ready-to-deploy in safety-critical domains -- from surgical robotics to autonomous drones. In contrast to recent methods such as Group Relative Policy Optimization (GRPO), PPO-BR offers a unified entropy-reward mechanism applicable to both language models and general reinforcement learning environments.

This manuscript builds upon an earlier version posted to TechRxiv. This arXiv version includes an updated comparison with GRPO (Group Relative Policy Optimization)