Gradient-Descent for Randomized Controllers under Partial Observability.
Linus HeckJip SpelSebastian JungesJoshua MoermanJoost-Pieter KatoenPublished in: CoRR (2021)
Keyphrases
- partial observability
- reinforcement learning
- partially observable
- control system
- planning problems
- belief state
- belief space
- objective function
- markov decision process
- planning under partial observability
- control strategy
- partial information
- partially observable markov decision processes
- state space
- domain specific
- graphical models