Asynchronous Value Iteration for Markov Decision Processes with Continuous State Spaces.
Xiangyu YangJian-Qiang HuJiaqiao HuYijie PengPublished in: WSC (2020)
Keyphrases
- markov decision processes
- continuous state spaces
- state space
- action space
- optimal policy
- policy iteration
- finite state
- reinforcement learning
- dynamic programming
- reinforcement learning algorithms
- decision processes
- continuous state
- factored mdps
- partially observable markov decision processes
- markov decision process
- finite horizon
- average reward
- stochastic games
- planning under uncertainty
- infinite horizon
- average cost
- heuristic search
- search algorithm
- stochastic shortest path
- partially observable
- optimal control
- real valued
- multi agent