Reinforcement Learning of Markov Decision Processes with Peak Constraints.
Ather GattamiPublished in: CoRR (2019)
Keyphrases
- markov decision processes
- reinforcement learning
- optimal policy
- state space
- reinforcement learning algorithms
- finite state
- policy iteration
- action space
- dynamic programming
- average reward
- partially observable
- planning under uncertainty
- model based reinforcement learning
- state and action spaces
- reachability analysis
- finite horizon
- transition matrices
- markov decision process
- state abstraction
- decision theoretic planning
- factored mdps
- action sets
- reward function
- decision processes
- infinite horizon
- policy evaluation
- average cost
- multi agent
- markov decision problems
- function approximation
- learning algorithm
- least squares
- optimal control
- partially observable markov decision processes