• Corpus ID: 220920150

Improving Multi-Agent Cooperation using Theory of Mind

  title={Improving Multi-Agent Cooperation using Theory of Mind},
  author={Terence X. Lim and Sidney Tio and Desmond C. Ong},
Recent advances in Artificial Intelligence have produced agents that can beat human world champions at games like Go, Starcraft, and Dota2. However, most of these models do not seem to play in a human-like manner: People infer others' intentions from their behaviour, and use these inferences in scheming and strategizing. Here, using a Bayesian Theory of Mind (ToM) approach, we investigated how much an explicit representation of others' intentions improves performance in a cooperative game. We… 

Figures from this paper

ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind

The proposed model not only outperforms the state-of-the-art methods on target coverage rate and communication efficiency, but also shows good generalization across different scales of the environment.

A Brain-Inspired Theory of Mind Spiking Neural Network for Reducing Safety Risks of Other Agents

A brain-inspired theory of mind spiking neural network (ToM-SNN) model is proposed to enable agents to perceive such risk-inducing errors inside others' mental states and make decisions to help others when necessary.



Finding Friend and Foe in Multi-Agent Games

The DeepRole algorithm is developed, a multi-agent reinforcement learning agent that is tested on The Resistance: Avalon, the most popular hidden role game and finds that DeepRole outperforms human players as both a cooperator and a competitor.

Help or Hinder: Bayesian Models of Social Goal Inference

A model for how people can infer social goals from actions, based on inverse planning in multiagent Markov decision problems (MDPs), is proposed and behavioral evidence is presented in support of this model over a simpler, perceptual cue-based alternative.

Grandmaster level in StarCraft II using multi-agent reinforcement learning

The agent, AlphaStar, is evaluated, which uses a multi-agent reinforcement learning algorithm and has reached Grandmaster level, ranking among the top 0.2% of human players for the real-time strategy game StarCraft II.

Results of the First Annual Human-Agent League of the Automated Negotiating Agents Competition

By introducing a new human-agent negotiating platform to the research community at large, this work facilitated new advancements in human-aware agents and succeeded in pushing the envelope in agent design, and creating a corpus of useful human- agent interaction data.

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

This paper generalizes the AlphaZero approach into a single AlphaZero algorithm that can achieve superhuman performance in many challenging games, and convincingly defeated a world champion program in the games of chess and shogi (Japanese chess), as well as Go.

Deal or No Deal? End-to-End Learning of Negotiation Dialogues

For the first time, it is shown it is possible to train end-to-end models for negotiation, which must learn both linguistic and reasoning skills with no annotated dialogue states, and this technique dramatically improves performance.

Mastering the game of Go with deep neural networks and tree search

Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.

Monte Carlo Sampling Methods for Approximating Interactive POMDPs

A general method for obtaining approximate solutions of I-POMDPs based on particle filtering (PF) is described and the interactive PF is introduced, which descends the levels of the interactive belief hierarchies and samples and propagates beliefs at each level.