Shared Autonomy via Deep Reinforcement Learning.

Siddharth Reddy Sergey Levine Anca D. Dragan

Published in: CoRR (2018)

Keyphrases

reinforcement learning
function approximation
optimal policy
learning algorithm
state space
markov decision processes
learning capabilities

multi agent
multi agent systems
model free
information systems
cooperative
optimal control
multi agent reinforcement learning

control problems
continuous state
direct policy search
policy search
adjustable autonomy
real world
reinforcement learning algorithms

temporal difference
dynamic environments
evolutionary algorithm
learning process
artificial intelligence
machine learning