most citedControlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics

53 citations · 53 across the 2 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2021

Automating Control of Overestimation Bias for Reinforcement Learning

Arsenii Kuznetsov, Alexander Grishin, Artem Tsypin +3

Overestimation bias control techniques are used by the majority of high-performing off-policy reinforcement learning algorithms. However, most of these techniques rely on pre-defin…

cs.LG2020★ 53 cited

Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics

Arsenii Kuznetsov, Pavel Shvechikov, Alexander Grishin +1

The overestimation bias is one of the major impediments to accurate off-policy learning. This paper investigates a novel way to alleviate the overestimation bias in a continuous co…