Optimal Planning Over Long and Infinite Horizons for Achieving Independent Partially-Observable Tasks That Evolve Over Time.
Anahita Mohseni-KabirManuela VelosoMaxim LikhachevPublished in: IEEE Robotics Autom. Lett. (2021)
Keyphrases
- partially observable
- optimal planning
- planning domains
- infinite horizon
- decision problems
- state space
- reinforcement learning
- dynamical systems
- markov decision processes
- heuristic search
- domain independent
- partial observations
- planning problems
- belief state
- computational complexity
- admissible heuristics
- general purpose