Interval Markov Decision Processes with Continuous Action-Spaces.
Giannis DelimpaltadakisMorteza LahijanianManuel Mazo Jr.Luca LaurentiPublished in: CoRR (2022)
Keyphrases
- action space
- markov decision processes
- state space
- state and action spaces
- finite state
- continuous state
- control policies
- continuous state spaces
- reinforcement learning
- dynamic programming
- optimal policy
- reinforcement learning algorithms
- finite horizon
- markov decision process
- continuous action
- policy iteration
- decision processes
- infinite horizon
- action selection
- average reward
- stochastic games
- average cost
- planning under uncertainty
- function approximators
- stochastic processes
- multi agent