Semi-Infinitely Constrained Markov Decision Processes and Efficient Reinforcement Learning.
Liangyu ZhangYang PengWenhao YangZhihua ZhangPublished in: CoRR (2023)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- state space
- reinforcement learning algorithms
- policy iteration
- finite state
- transition matrices
- dynamic programming
- decision theoretic planning
- model based reinforcement learning
- partially observable
- average reward
- average cost
- markov decision process
- risk sensitive
- planning under uncertainty
- action sets
- state and action spaces
- infinite horizon
- factored mdps
- decision processes
- function approximation
- action space
- reachability analysis
- semi markov decision processes
- machine learning
- stochastic games
- approximate dynamic programming
- continuous state spaces
- state abstraction
- multi agent
- control problems
- temporal difference
- total reward