UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning

Abstract

VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this enables easy decentralization of the learned policy, the restricted joint action value function can prevent them from solving tasks that require significant coordination between agents at a given timestep. We show that this problem can be overcome by improving the joint exploration of all agents during training. Specifically, we propose a novel MARL approach called Universal Value Exploration (UneVEn) that learns a set of related tasks simultaneously with a linear decomposition of universal successor features. With the policies of already solved related tasks, the joint exploration process of all agents can be improved to help them achieve better coordination. Empirical results on a set of exploration games, challenging cooperative predator-prey tasks requiring significant coordination among agents, and StarCraft II micromanagement benchmarks show that UneVEn can solve tasks where other state-of-the-art MARL methods fail.

Published at ICML 2021

References in corpus (11)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Learning a Generic Value-Selection Heuristic Inside a Constraint Programming Solver
• QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
• QPLEX: Duplex Dueling Multi-Agent Q-Learning
• MAVEN: Multi-Agent Variational Exploration
• Autocurricula and the Emergence of Innovation from Social Interaction: A Manifesto for Multi-Agent Intelligence Research
• RODE: Learning Roles to Decompose Multi-Agent Tasks
• Advantages and Limitations of using Successor Features for Transfer in Reinforcement Learning
• Universal Successor Features Approximators
• Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning
• Symmetry Learning for Function Approximation in Reinforcement Learning

Cited by in corpus (4)

• Regularized Softmax Deep Multi-Agent $Q$-Learning
• MARL with General Utilities via Decentralized Shadow Reward Actor-Critic
• Model based Multi-agent Reinforcement Learning with Tensor Decompositions
• Reinforcement Learning in Factored Action Spaces using Tensor Decompositions