Partial Observability during DRL for Robot Control.
Lingheng MengRob GorbetDana KulicPublished in: CoRR (2022)
Keyphrases
- robot control
- partial observability
- reinforcement learning
- mobile robot
- autonomous robots
- partially observable
- planning problems
- belief space
- subsumption architecture
- belief state
- planning under partial observability
- markov decision process
- optimal control
- partial information
- temporal difference
- partially observable markov decision processes
- machine learning
- pid controller
- function approximation
- expert systems
- learning algorithm