A Tensor Network Approach to Finite Markov Decision Processes.
Edward GillmanDominic C. RoseJuan P. GarrahanPublished in: CoRR (2020)
Keyphrases
- markov decision processes
- state and action spaces
- optimal policy
- state space
- finite state
- transition matrices
- reinforcement learning
- dynamic programming
- policy iteration
- decision theoretic planning
- average reward
- reachability analysis
- risk sensitive
- reinforcement learning algorithms
- action space
- decision processes
- factored mdps
- action sets
- finite horizon
- planning under uncertainty
- markov decision process
- average cost
- infinite horizon
- partially observable
- model based reinforcement learning
- stationary policies
- data mining
- state abstraction
- reward function
- search space
- real time dynamic programming