Macro-Action-Based Deep Multi-Agent Reinforcement Learning

2020-04-18 · Yuchen Xiao, Joshua Hoffman, Christopher Amato

In real-world multi-robot systems, performing high-quality, collaborative behaviors requires robots to asynchronously reason about high-level action selection at varying time durations. Macro-Action Decentralized Partially Observable Markov Decision Processes (MacDec-POMDPs) provide a general framework for asynchronous decision making under uncertainty in fully cooperative multi-agent tasks. However, multi-agent deep reinforcement learning methods have only been developed for (synchronous) primitive-action problems. This paper proposes two Deep Q-Network (DQN) based methods for learning decentralized and centralized macro-action-value functions with novel macro-action trajectory replay buffers introduced for each case. Evaluations on benchmark problems and a larger domain demonstrate the advantage of learning with macro-actions over primitive-actions and the scalability of our approaches.

📄 PDF Abstract BibTeX arXiv:2004.08646

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingDecision Making Under UncertaintyDeep Reinforcement LearningMulti-agent Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Macro-Action-Based Multi-Agent/Robot Deep Reinforcement Learning under Partial Observability

2022-09-20 · Yuchen Xiao

The state-of-the-art multi-agent reinforcement learning (MARL) methods have provided promising solutions to a variety of complex problems. Yet, these methods all assume that agents perform synchronized primitive-action e…

Decision Making Decision Making Under Uncertainty Deep Reinforcement Learning Multi-agent Reinforcement Learning+2

Reusability and Transferability of Macro Actions for Reinforcement Learning

2019-08-05 · Yi-Hsiang Chang, Kuan-Yu Chang, Henry Kuo, Chun-Yi Lee

Conventional reinforcement learning (RL) typically determines an appropriate primitive action at each timestep. However, by using a proper macro action, defined as a sequence of primitive actions, an agent is able to byp…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action Quantization

2026-05-29 · Usman Nizamani, M. Shaheer Luqman, Fawad Javed Fateh, Ali Shah Ali 외 arxiv

Human-like agents are a long-standing goal of artificial intelligence. Despite strong performance, most reinforcement learning (RL) agents remain reward-driven and often exhibit behaviors that differ from humans, limitin…

Reinforcement Learning

Hierarchical Reinforcement Learning for Multi-agent MOBA Game

2019-01-23 · Zhijian Zhang, Haozheng Li, Luo Zhang, Tianyin Zheng 외

Real Time Strategy (RTS) games require macro strategies as well as micro strategies to obtain satisfactory performance since it has large state space, action space, and hidden information. This paper presents a novel hie…

Hierarchical Reinforcement Learning Imitation Learning reinforcement-learning Reinforcement Learning+2

Leveraging Topological Maps in Deep Reinforcement Learning for Multi-Object Navigation

2023-10-16 · Simon Hakenes, Tobias Glasmachers

This work addresses the challenge of navigating expansive spaces with sparse rewards through Reinforcement Learning (RL). Using topological maps, we elevate elementary actions to object-oriented macro actions, enabling a…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)