Improving Sample Efficiency in Evolutionary RL Using Off-Policy Ranking.

Eshwar S. R Shishir Kolathaya Gugan Thoppe

Published in: VALUETOOLS (2023)

Keyphrases

reinforcement learning
genetic algorithm
evolutionary computation
ranking algorithm
ranking functions
multi agent
state space
web search
computational complexity
genetic programming
optimal policy
semi supervised
sample size
markov decision processes
ranked list
high efficiency