Leveraging Procedural Generation to Benchmark Reinforcement Learning.

Karl Cobbe Christopher Hesse Jacob Hilton John Schulman

Published in: CoRR (2019)

Keyphrases

reinforcement learning
markov decision processes
function approximation
multi agent
generation process

optimal policy
robotic control
stochastic approximation
learning problems
real world

object oriented
state space
dynamic programming
comparative analysis
reinforcement learning algorithms

learning process
decision trees
policy search
data mining