paper-with-me

홈 › Papers

Simple Policy Optimization

2024-01-29 · Zhengpeng Xie, Qiang Zhang, Fan Yang, Marco Hutter, Renjing Xu

Model-free reinforcement learning algorithms have seen remarkable progress, but key challenges remain. Trust Region Policy Optimization (TRPO) is known for ensuring monotonic policy improvement through conservative updates within a trust region, backed by strong theoretical guarantees. However, its reliance on complex second-order optimization limits its practical efficiency. Proximal Policy Optimization (PPO) addresses this by simplifying TRPO's approach using ratio clipping, improving efficiency but sacrificing some theoretical robustness. This raises a natural question: Can we combine the strengths of both methods? In this paper, we introduce Simple Policy Optimization (SPO), a novel unconstrained first-order algorithm. By slightly modifying the policy loss used in PPO, SPO can achieve the best of both worlds. Our new objective improves upon ratio clipping, offering stronger theoretical properties and better constraining the probability ratio within the trust region. Empirical results demonstrate that SPO outperforms PPO with a simple implementation, particularly for training large, complex network architectures end-to-end.

📄 PDF Abstract BibTeX arXiv:2401.16025

Code (1)

myrepositories-hub/simple-policy-optimization 공식 구현 pytorch

Tasks

MuJoCo

Methods 이 논문이 사용한 방법론

Entropy Regularization 설명 없음
PPO Proximal Policy Optimization, or PPO, is a policy gradient method for reinforcement learning. The motivation was to have an algorithm with the data efficiency and reliable…
TRPO Trust Region Policy Optimization, or TRPO, is a policy gradient method in reinforcement learning that avoids parameter updates that change the policy too much with a KL…

Similar Papers 제목 키워드 기반

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)

Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex

2026-05-07 · Yun Qu, Qi Wang, Yixiu Mao, Heming Zou 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existing recipes, group-based policy gradient i…

Reinforcement Learning

First Order Constrained Optimization in Policy Space

2020-02-16 · NeurIPS 2020 12 · Yiming Zhang, Quan Vuong, Keith W. Ross

In reinforcement learning, an agent attempts to learn high-performing behaviors through interacting with the environment, such behaviors are often quantified in the form of a reward function. However some aspects of beha…

Reinforcement Learning

Empirical Likelihood for Contextual Bandits

2019-06-07 · NeurIPS 2020 12 · Nikos Karampatziakis, John Langford, Paul Mineiro

We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. To this end we apply empirical likelihood techniques to formulate our estimator a…

Multi-Armed Bandits

Simple Nearest Neighbor Policy Method for Continuous Control Tasks

2018-01-01 · ICLR 2018 1 · Elman Mansimov, Kyunghyun Cho

We design a new policy, called a nearest neighbor policy, that does not require any optimization for simple, low-dimensional continuous control tasks. As this policy does not require any optimization, it allows us to inv…

continuous-controlContinuous Control