Reward Shaping for Model-Based Bayesian Reinforcement Learning.
Hyeoneun KimWoosang LimKanghoon LeeYung-Kyun NohKee-Eung KimPublished in: AAAI (2015)
Keyphrases
- bayesian reinforcement learning
- reward shaping
- reinforcement learning
- optimal policy
- markov decision problems
- model free
- reinforcement learning algorithms
- monte carlo tree search
- linear programming
- markov decision processes
- complex domains
- state space
- partially observable markov decision processes
- decision making
- monte carlo
- machine learning
- temporal difference
- dynamic programming