Optimal Policies for Platooning and Ride Sharing in Autonomy-Enabled Transportation.
Aviv AdlerDavid MiculescuSertac KaramanPublished in: WAFR (2016)
Keyphrases
- optimal policy
- markov decision processes
- state space
- reinforcement learning
- decision problems
- finite horizon
- dynamic programming
- long run
- sufficient conditions
- decision making
- infinite horizon
- finite state
- average cost
- multistage
- average reward
- state dependent
- lost sales
- dynamic programming algorithms
- multi agent systems
- initial state
- control policies
- average reward reinforcement learning
- markov decision process
- transportation problem
- objective function
- serial inventory systems
- bayesian reinforcement learning
- policy iteration
- inventory level
- markov decision problems
- linear programming
- finite number
- belief revision
- markov chain