Simplified Action Decoder For Deep Multi-agent Reinforcement Learning

Abstract

In recent years we have seen fast progress on a number of benchmark problems in AI, with modern methods achieving near or super human performance in Go, Poker and Dota. One common aspect of all of these challenges is that they are by design adversarial or, technically speaking, zero-sum. In contrast to these settings, success in the real world commonly requires humans to collaborate and communicate with others, in settings that are, at least partially, cooperative. In the last year, the card game Hanabi has been established as a new benchmark environment for AI to fill this gap. In particular, Hanabi is interesting to humans since it is entirely focused on theory of mind, i.e., the ability to effectively reason over the intentions, beliefs and point of view of other agents when observing their actions. Learning to be informative when observed by others is an interesting challenge for Reinforcement Learning (RL): Fundamentally, RL requires agents to explore in order to discover good pol

Stats

• citations0
• S2 citations—
• github stars102
• HF likes0
• heat score4.03
• arxiv keyhu2019simplified

Related papers

• Bayesian Action Decoder For Deep Multi-agent Reinforcement Learning (2018)0.00
• Theory Of Mind For Deep Reinforcement Learning In Hanabi (2021)0.00
• Reinforcement Learning On Human Decision Models For Uniquely Collaborative AI Teammates (2021)0.00
• Deep Multiagent Reinforcement Learning: Challenges And Directions (2021)0.00
• Analysing Factorizations Of Action-value Networks For Cooperative Multi-agent Reinforcement Learning (2019)2.26
• A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
• Multi-agent Reinforcement Learning: A Report On Challenges And Approaches (2018)0.00
• Deep Reinforcement Learning For Multi-agent Systems: A Review Of Challenges, Solutions And Applications (2018)22.57