Login / Signup
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research.
Mikayel Samvelyan
Robert Kirk
Vitaly Kurin
Jack Parker-Holder
Minqi Jiang
Eric Hambro
Fabio Petroni
Heinrich Küttler
Edward Grefenstette
Tim Rocktäschel
Published in:
CoRR (2021)
Keyphrases
</>
open ended
reinforcement learning
learning outcomes
state space
function approximation
reinforcement learning algorithms
multiple choice
multi agent
optimal policy
model free
machine learning
learning algorithm
markov decision processes
temporal difference
shared knowledge
affect detection