Sparse Markov Decision Processes with Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning.
Kyungjae LeeSungjoon ChoiSonghwai OhPublished in: CoRR (2017)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- reinforcement learning algorithms
- state space
- finite state
- policy iteration
- decision theoretic planning
- dynamic programming
- state and action spaces
- action space
- reward function
- markov decision process
- average reward
- finite horizon
- infinite horizon
- model based reinforcement learning
- factored mdps
- reachability analysis
- bayesian networks
- partially observable
- temporal difference
- planning under uncertainty
- function approximation
- action sets
- transition matrices
- model free
- continuous state spaces