Comparing exploration strategies for Q-learning in random stochastic mazes.
Arryon D. TijsmaMadalina M. DruganMarco A. WieringPublished in: SSCI (2016)
Keyphrases
- exploration strategy
- reinforcement learning
- action selection
- stochastic approximation
- locally optimal
- unknown environments
- randomly generated
- multi agent
- learning algorithm
- search strategies
- evolutionary algorithm
- cooperative
- function approximation
- learning automata
- markov decision processes
- mobile robot
- reinforcement learning methods
- dynamic programming
- potential field