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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autore principale: Rahman, Ben
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913855397953536
author Rahman, Ben
author_facet Rahman, Ben
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_17714
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization
Rahman, Ben
Machine Learning
Artificial Intelligence
Computation and Language
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.
title PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2505.17714