Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions.
Tian TianKenny YoungRichard S. SuttonPublished in: NeurIPS (2022)
Keyphrases
- markov decision processes
- state space
- heuristic search
- decision theoretic
- markov decision chains
- markov decision process
- belief space
- partially observable markov
- asynchronous communication
- policy iteration
- stochastic shortest path
- asynchronous cellular automata
- asynchronous circuits
- data sets
- optimal policy
- dynamic programming
- case study
- average reward
- decision processes
- discussion forums
- delay insensitive
- online discussion