Dead-ends and Secure Exploration in Reinforcement Learning.

Mehdi Fatemi Shikhar Sharma Harm van Seijen Samira Ebrahimi Kahou

Published in: ICML (2019)

Keyphrases

reinforcement learning
dead ends
path planning
search tree
state space
multi agent
heuristic functions
dynamic programming
learning algorithm
markov decision processes
optimal policy
backtracking algorithm