Non-linear dynamics in multiagent reinforcement learning algorithms.
Sherief AbdallahVictor R. LesserPublished in: AAMAS (3) (2008)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- multi agent
- stochastic games
- model free
- state space
- markov decision processes
- reinforcement learning problems
- multiagent systems
- temporal difference
- eligibility traces
- reinforcement learning methods
- dynamical systems
- function approximation
- cooperative
- learning algorithm
- reward function
- dynamic environments
- autonomous agents
- markov chain
- artificial neural networks
- policy search
- partially observable environments
- single agent
- search space
- optimal policy
- function approximators
- support vector
- machine learning
- reward shaping