Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning.

Arjun Manoharan Rahul Ramesh Balaraman Ravindran

Published in: ECML/PKDD (2) (2020)

Keyphrases

function approximation
reinforcement learning
sequential decision making
optimal policy
main contribution
neural network
markov decision process
reinforcement learning problems
learning algorithm
multi agent
optical flow
probabilistic model
theoretical framework
low complexity