Planning with Hierarchical Temporal Memory for Deterministic Markov Decision Problem.
Petr KuderovAleksandr I. PanovPublished in: ICAART (2) (2021)
Keyphrases
- markov decision problems
- hierarchical temporal memory
- partially observable
- linear programming
- decision theoretic
- state space
- reinforcement learning
- optimal policy
- decision processes
- planning problems
- queueing networks
- expected utility
- transition probabilities
- utility function
- linear program
- ai planning
- heuristic search
- blocks world
- dynamic programming
- planning domains
- least squares
- markov decision processes
- average cost
- policy iteration
- multi agent