We use reinforcement learning (RL) to compute strategies for multiagent soccer teams. RL may pro t signi cantly from world models (WMs) estimating state transition probabilities an...
Recent decision-theoric planning algorithms are able to find optimal solutions in large problems, using Factored Markov Decision Processes (fmdps). However, these algorithms need ...
Thomas Degris, Olivier Sigaud, Pierre-Henri Wuille...
Reinforcement learning is a popular and successful framework for many agent-related problems because only limited environmental feedback is necessary for learning. While many algo...
— We propose a novel approach for acquisition and development of behaviors through observation in multi-agent environment. Observed behaviors of others give fruitful hints for a ...
This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...