i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops.
Saminda AbeyruwanLaura GraesserDavid B. D'AmbrosioAvi SinghAnish ShankarAlex BewleyPannag R. SanketiPublished in: CoRR (2022)
Keyphrases
- human robot interaction
- reinforcement learning
- robot programming
- manipulation tasks
- service robots
- human robot
- optimal policy
- real robot
- humanoid robot
- human centered
- gesture recognition
- lower bound
- pointing gestures
- policy search
- robotic systems
- markov decision process
- control policies
- upper bound
- markov decision problems
- mobile robot
- machine learning
- gaze control
- multi agent
- action selection
- temporal difference
- state space
- learning process
- partially observable markov decision processes
- learning algorithm
- natural language
- high dimensional
- robot control
- robot navigation
- model free
- human interaction
- software engineering
- markov decision processes