E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

2022-12-05 · Can Chang, Ni Mu, Jiajun Wu, Ling Pan, Huazhe Xu

A critical challenge in multi-agent reinforcement learning(MARL) is for multiple agents to efficiently accomplish complex, long-horizon tasks. The agents often have difficulties in cooperating on common goals, dividing complex tasks, and planning through several stages to make progress. We propose to address these challenges by guiding agents with programs designed for parallelization, since programs as a representation contain rich structural and semantic information, and are widely used as abstractions for long-horizon tasks. Specifically, we introduce Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance(E-MAPP), a novel framework that leverages parallel programs to guide multiple agents to efficiently accomplish goals that require planning over $10+$ stages. E-MAPP integrates the structural information from a parallel program, promotes the cooperative behaviors grounded in program semantics, and improves the time efficiency via a task allocator. We conduct extensive experiments on a series of challenging, long-horizon cooperative tasks in the Overcooked environment. Results show that E-MAPP outperforms strong baselines in terms of the completion rate, time efficiency, and zero-shot generalization ability by a large margin.

📄 PDF Abstract BibTeX arXiv:2212.02064

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Zero-shot Generalization

Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces

2024-10-21 · Anjiang Wei, Allen Nie, Thiago S. F. X. Teixeira, Rohan Yadav 외

Modern scientific discovery increasingly relies on high-performance computing for complex modeling and simulation. A key challenge in improving parallel program performance is efficiently mapping tasks to processors and …

Code Generation scientific discovery

Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping

2025-07-22 · Srivatsan Krishnan, Jason Jabbour, Dan Zhang, Natasha Jaques 외 arxiv

Mapping deep neural networks (DNNs) to hardware is critical for optimizing latency, energy consumption, and resource utilization, making it a cornerstone of high-performance accelerator design. Due to the vast and comple…

Multi-agent Reinforcement Learning

Synthesizing Optimal Parallelism Placement and Reduction Strategies on Hierarchical Systems for Deep Learning

2021-10-20 · Ningning Xie, Tamara Norman, Dominik Grewe, Dimitrios Vytiniotis

We present a novel characterization of the mapping of multiple parallelism forms (e.g. data and model parallelism) onto hierarchical accelerator systems that is hierarchy-aware and greatly reduces the space of software-t…

GPU Program Synthesis

MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning

2021-06-05 · Ming Zhou, Ziyu Wan, Hanjing Wang, Muning Wen 외

Population-based multi-agent reinforcement learning (PB-MARL) refers to the series of methods nested with reinforcement learning (RL) algorithms, which produces a self-generated sequence of tasks arising from the coupled…

Atari Games CPU Distributed Computing Multi-agent Reinforcement Learning+3

Multiagent Value Iteration Algorithms in Dynamic Programming and Reinforcement Learning

2020-05-04 · Dimitri Bertsekas

We consider infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. In an earlier work we introduced a policy iterati…

reinforcement-learning Reinforcement Learning (RL)