Sparse Markov Decision Processes With Causal Sparse Tsallis Entropy Regularization for Reinforcement Learning.
Kyungjae LeeSungjoon ChoiSonghwai OhPublished in: IEEE Robotics Autom. Lett. (2018)
Keyphrases
- markov decision processes
- reinforcement learning
- reinforcement learning algorithms
- optimal policy
- state space
- transition matrices
- finite state
- dynamic programming
- partially observable
- policy iteration
- action space
- decision theoretic planning
- model based reinforcement learning
- reachability analysis
- infinite horizon
- planning under uncertainty
- state and action spaces
- finite horizon
- average reward
- average cost
- state abstraction
- markov decision process
- function approximation
- data mining
- sufficient conditions
- stochastic games
- temporal difference
- long run
- real valued