Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation.
Kenzo Lobos-TsunekawaTatsuya HaradaPublished in: IROS (2020)
Keyphrases
- partial observability
- visual navigation
- reinforcement learning
- partially observable
- belief state
- collision avoidance
- planning problems
- markov decision process
- belief space
- state space
- markov decision processes
- learning agent
- visual odometry
- learning process
- dynamic environments
- optimal policy
- partially observable markov decision processes
- multi agent
- computer vision