Construction of a learning agent handling its rewards according to environmental situations.
Koichi MoriyamaMasayuki NumaoPublished in: AAMAS (2002)
Keyphrases
- learning agent
- reinforcement learning
- reward function
- state space
- solving problems
- reinforcement learning algorithms
- learning algorithm
- selective perception
- markov decision processes
- learning process
- training data
- learning capabilities
- dynamic environments
- model free
- function approximation
- decision problems
- heuristic search
- computational complexity