Demonstration-Guided Deep Reinforcement Learning of Control Policies for Dexterous Human-Robot Interaction.
Sammy ChristenStefan StevsicOtmar HilligesPublished in: ICRA (2019)
Keyphrases
- control policies
- human robot interaction
- reinforcement learning
- robot programming
- humanoid robot
- manipulation tasks
- optimal policy
- continuous state
- control policy
- human robot
- action space
- state space
- motion planning
- gesture recognition
- model free
- control strategies
- service robots
- multi agent
- multi modal
- learning algorithm
- reward function
- markov decision processes
- motion control
- finite horizon
- pointing gestures
- infinite horizon
- real robot
- long run
- control system
- markov decision process
- robot control
- optimal control
- decision problems
- dynamic programming
- computer vision