Adaptive State Space Quantisation For Reinforcement Learning Of collision-free navigation.
Ben J. A. KröseJoris W. M. van DamPublished in: IROS (1992)
Keyphrases
- state space
- reinforcement learning
- reinforcement learning algorithms
- markov decision processes
- heuristic search
- optimal policy
- adaptive control
- markov chain
- function approximation
- action space
- dynamic programming
- state variables
- state abstraction
- goal state
- robotic control
- markov decision process
- continuous state spaces
- search space
- data sets
- model free
- state and action spaces
- neural network
- learning algorithm
- learning agent
- markov decision problems
- multi agent systems
- actor critic
- multi agent
- reinforcement learning methods
- learning problems
- hidden markov models
- reward function
- particle filter
- learning tasks