paper-with-me

홈 › Papers

Optimistic Policy Regularization

2026-03-06 · Mai Pham, Vikrant Vaze, Peter Chin arxiv

Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering globally optimal strategies. We introduce Optimistic Policy Regularization (OPR), a lightweight mechanism designed to preserve and reinforce historically successful trajectories during policy optimization. OPR maintains a dynamic buffer of high-performing episodes and biases learning toward these behaviors through directional log-ratio reward shaping and an auxiliary behavioral cloning objective. When instantiated on Proximal Policy Optimization (PPO), OPR substantially improves sample efficiency on the Arcade Learning Environment. Across 49 Atari games evaluated at the 10-million step benchmark, OPR achieves the highest score in 22 environments despite baseline methods being reported at the standard 50-million step horizon. Beyond arcade benchmarks, OPR also generalizes to the CAGE Challenge 2 cyber-defense environment, surpassing the competition-winning Cardiff agent while using the same PPO architecture. These results demonstrate that anchoring policy updates to empirically successful trajectories can improve both sample efficiency and final performance.

📄 PDF Abstract BibTeX arXiv:2603.06793

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningAtari Games

Similar Papers 제목 키워드 기반

Variational Bayesian Optimistic Sampling

2021-10-29 · NeurIPS 2021 12 · Brendan O'Donoghue, Tor Lattimore

We consider online sequential decision problems where an agent must balance exploration and exploitation. We derive a set of Bayesian `optimistic' policies which, in the stochastic multi-armed bandit case, includes the T…

Thompson Sampling

Achieving Logarithmic Regret in KL-Regularized Zero-Sum Markov Games

2025-10-15 · Anupam Nayak, Tong Yang, Osman Yagan, Gauri Joshi 외 arxiv

Reverse Kullback-Leibler (KL) divergence-based regularization with respect to a fixed reference policy is widely used in modern reinforcement learning to preserve the desired traits of the reference policy and sometimes …

Reinforcement Learning

Online Regularization towards Always-Valid High-Dimensional Dynamic Pricing

2020-07-05 · Chi-Hua Wang, Zhanyu Wang, Will Wei Sun, Guang Cheng

Devising dynamic pricing policy with always valid online statistical learning procedure is an important and as yet unresolved problem. Most existing dynamic pricing policy, which focus on the faithfulness of adopted cust…

validVocal Bursts Intensity Prediction

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

2023-05-18 · NeurIPS 2023 11 · Qinghua Liu, Gellért Weisz, András György, Chi Jin 외

While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy optimization remains rather limited -- they …

Reinforcement Learning (RL)

Optimistic Proximal Policy Optimization

2019-06-25 · Takahisa Imagawa, Takuya Hiraoka, Yoshimasa Tsuruoka

Reinforcement Learning, a machine learning framework for training an autonomous agent based on rewards, has shown outstanding results in various domains. However, it is known that learning a good policy is difficult in a…

BIG-bench Machine Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)