Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning

24 November 2021

Tim Welschehold

Wolfram Burgard

Papers citing "Adaptively Calibrated Critic Estimates for Deep Reinforcement Learning"

3 / 3 papers shown

Title
Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning Edoardo Cetin Oya Celiktutan OffRL 32 16 0 07 Oct 2021
Controlling Overestimation Bias with Truncated Mixture of Continuous Distributional Quantile Critics Arsenii Kuznetsov Pavel Shvechikov Alexander Grishin Dmitry Vetrov 136 184 0 08 May 2020
Off-Policy Actor-Critic T. Degris Martha White R. Sutton OffRL CML 155 221 0 22 May 2012