Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs.
Dominik StraubMatthias SchultheisHeinz KoepplConstantin A. RothkopfPublished in: NeurIPS (2023)
Keyphrases
- optimal control
- infinite horizon
- partially observable
- reinforcement learning
- partial observability
- bayesian networks
- optimal control problems
- average cost
- markov decision processes
- control strategy
- dynamic programming
- dynamical systems
- state space
- partial observations
- long run
- computational complexity
- action models
- objective function
- decision making