Aggregation of tiling-based reinforcement learning algorithms.
Ju JiangMohamed S. KamelPublished in: SMC (2007)
Keyphrases
- reinforcement learning algorithms
- reinforcement learning
- markov decision processes
- model free
- state space
- reinforcement learning problems
- temporal difference
- reinforcement learning methods
- learning algorithm
- eligibility traces
- function approximation
- partially observable environments
- stochastic games
- reward function
- multiagent reinforcement learning
- policy gradient
- web pages
- tabula rasa
- function approximators
- neural network
- policy search
- artificial neural networks
- decision making