Leader-Follower MDP Models with Factored State Space and Many Followers - Followers Abstraction, Structured Dynamics and State Aggregation.
Régis SabbadinAnne-France VietPublished in: ECAI (2016)
Keyphrases
- state space
- markov decision processes
- markov decision process
- state abstraction
- state variables
- reinforcement learning
- dynamical systems
- dynamic programming
- heuristic search
- optimal policy
- action space
- factored markov decision processes
- partially observable
- particle filter
- experimental data
- factored mdps
- initial state
- linear model
- reward function
- belief state
- markov decision problems