Generation of Roles in Reinforcement Learning Considering Redistribution of Reward between Agents.
Masahiro NakaharaYuko OsanaPublished in: SMC (2009)
Keyphrases
- reinforcement learning
- multi agent
- agent receives
- learning agent
- learning agents
- action selection
- single agent
- multi agent systems
- multi agent environments
- role assignment
- reinforcement learning agents
- robocup soccer
- function approximation
- optimal policy
- multi agent reinforcement learning
- multiple agents
- multiagent systems
- reinforcement learning algorithms
- cooperative
- reward function
- multiagent learning
- mobile agents
- state space
- software agents
- autonomous agents
- intelligent agents
- machine learning
- learning capabilities
- complex domains
- expected reward
- eligibility traces
- reward shaping
- model free
- agent architecture
- agent learns
- reward signal
- stochastic games
- markov decision processes
- partial observability
- learning algorithm
- solving problems
- learning process
- policy gradient
- average reward
- function approximators
- temporal difference
- coalition formation
- decentralized control
- artificial agents
- partially observable
- trust model
- partially observable environments
- dynamic programming
- agent technology
- decision theoretic