paper-with-me

Papers

Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning

2026-05-09 · Chulabhaya Wijesundara, Andrea Baisero, Zhongheng Li, Gregory Castañón, Alan Carlin, Christopher Amato arxiv

Centralized training with decentralized execution (CTDE) is a standard framework for cooperative multi-agent policy-gradient reinforcement learning, allowing agents to learn from joint information while acting from local observations. Ratio-based trust-region methods such as Multi-Agent Proximal Policy Optimization (MAPPO) and Multi-Agent Simple Policy Optimization (MASPO) update decentralized actors using per-agent probability ratios weighted by joint advantage estimates. Teammate non-stationarity increases the variance of these advantages, which in turn increases the variance in the local ratio updates. This exposes two method-specific failure modes: MAPPO's additive clipping removes gradients for outlier samples and weakens recovery from policy drift, while MASPO's soft quadratic penalty can allow probability collapse. We introduce Multi-Agent Ratio Symmetry (MARS), a novel policy optimization objective that replaces these additive ratio-based trust-region mechanisms with a multiplicatively symmetric geometric barrier. MARS preserves corrective gradients while assigning unbounded cost as probability ratios approach zero. Across 47 tasks spanning eight multi-agent environments, including novel JAX benchmarks PaxMen and AeroJAX, MARS matches or exceeds MAPPO and MASPO in aggregate environment-level performance. Ablations show that these gains arise from the geometry of the symmetric barrier rather than from flexible trust-region boundaries alone.

📄 PDF Abstract BibTeX arXiv:2605.09212

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Rethinking the Divergence Regularization in LLM RL

2026-06-08 · Jiarui Yao, Xiangxin Zhou, Penghui Qi, Wee Sun Lee 외 arxiv

Reinforcement learning (RL) has become a key component of post-training large language models (LLMs). In practice, LLM RL is often off-policy because of training-inference mismatch and policy staleness, making trust-regi…

Reinforcement Learning

Trust Region On-Policy Distillation

2026-05-31 · Xingrun Xing, Haoqing Wang, Boyan Gao, Ziheng Li 외 arxiv

On-Policy Distillation (OPD) is a fundamental technique for efficient post-training of large language models (LLMs), with broad applications in agent learning, multi-task enhancement, and model compression. However, OPD …

Mathematical ReasoningModel CompressionCode Generation

Differentiable Trust Region Layers for Deep Reinforcement Learning

2021-01-22 · ICLR 2021 1 · Fabian Otto, Philipp Becker, Ngo Anh Vien, Hanna Carolin Ziesche 외

Trust region methods are a popular tool in reinforcement learning as they yield robust policy updates in continuous and discrete action spaces. However, enforcing such trust regions in deep reinforcement learning is diff…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Learning to Constrain Policy Optimization with Virtual Trust Region

2022-04-20 · Hung Le, Thommen Karimpanal George, Majid Abdolshah, Dung Nguyen 외

We introduce a constrained optimization method for policy gradient reinforcement learning, which uses a virtual trust region to regulate each policy update. In addition to using the proximity of one single old policy as …

Atari GamesPolicy Gradient Methods

Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions

2022-10-20 · Antonio Terpin, Nicolas Lanzetti, Batuhan Yardim, Florian Dörfler 외

Policy Optimization (PO) algorithms have been proven particularly suited to handle the high-dimensionality of real-world continuous control tasks. In this context, Trust Region Policy Optimization methods represent a pop…

continuous-controlContinuous Control