End-to-end grasping policies for human-in-the-loop robots via deep reinforcement learning.
Mohammadreza SharifDeniz ErdogmusChristopher AmatoTaskin PadirPublished in: CoRR (2021)
Keyphrases
- end to end
- reinforcement learning
- human robot interaction
- optimal policy
- congestion control
- manipulation tasks
- robot control
- multipath
- high bandwidth
- policy search
- mobile robot
- ad hoc networks
- markov decision processes
- reward function
- real robot
- admission control
- vision system
- wireless ad hoc networks
- human users
- markov decision process
- transport layer
- real time
- multi robot
- computational complexity
- packet loss rate