Reinforcement Learning in Distributed Domains: Beyond Team Games.
David H. WolpertJoseph SillKagan TumerPublished in: IJCAI (2001)
Keyphrases
- reinforcement learning
- distributed systems
- transfer learning
- cooperative
- game theory
- multi agent
- video games
- learning agents
- partially observable domains
- learning algorithm
- distributed environment
- complex domains
- application domains
- peer to peer
- function approximation
- cross domain
- reinforcement learning algorithms
- temporal difference
- team members
- learning classifier systems
- machine learning
- multi agent reinforcement learning
- temporal difference learning
- dynamic programming
- mobile robot
- model free
- game theoretic
- game playing
- optimal control
- real world
- optimal policy
- markov decision processes
- learning experience