Multi-objectivization of reinforcement learning problems by reward shaping.
Tim BrysAnna HarutyunyanPeter VrancxMatthew E. TaylorDaniel KudenkoAnn NowéPublished in: IJCNN (2014)
Keyphrases
- reinforcement learning problems
- reinforcement learning algorithms
- reward shaping
- markov decision problems
- reinforcement learning
- model free
- markov decision processes
- state space
- reinforcement learning methods
- function approximation
- temporal difference
- function approximators
- learning algorithm
- policy iteration
- linear programming
- reward function
- expected utility
- optimal policy
- partially observable
- decision processes