Neural decoding systems using Markov Decision Processes.
Henrique DantasV. John MathewsSuzanne M. WendelkenTyler S. DavisGregory A. ClarkDavid J. WarrenPublished in: ICASSP (2017)
Keyphrases
- markov decision processes
- optimal policy
- finite state
- state space
- reinforcement learning
- dynamic programming
- reachability analysis
- decentralized control
- model based reinforcement learning
- policy iteration
- decision theoretic planning
- planning under uncertainty
- transition matrices
- neural network
- action sets
- average cost
- network architecture
- risk sensitive
- average reward
- infinite horizon
- state abstraction
- state and action spaces
- finite horizon