Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning.
Thomas G. DietterichGeorge TrimponiasZhitang ChenPublished in: ICML (2018)
Keyphrases
- state variables
- reinforcement learning
- state space
- reward function
- markov decision processes
- reinforcement learning algorithms
- heuristic search
- dynamic systems
- function approximation
- markov decision process
- partially observable
- optimal policy
- model free
- learning algorithm
- action space
- planning problems
- multi agent
- autoregressive
- dynamical systems
- random variables
- action selection
- dynamic programming
- machine learning
- reward shaping
- bayesian networks
- search algorithm
- sliding surface