Papers › Estimation Error Correction in Deep Reinforcement Learning for Deterministic...

Estimation Error Correction in Deep Reinforcement Learning for Deterministic Actor-Critic Methods

22 Sep 2021arXiv:2109.10736archive 2025-07-28

Baturay Saglam, Enes Duran, Dogan C. Cicek, Furkan B. Mutlu, Suleyman S. Kozat

In value-based deep reinforcement learning methods, approximation of value functions induces overestimation bias and leads to suboptimal policies. We show that in deep actor-critic methods that aim to overcome the overestimation bias, if the reinforcement signals received by the agent have a high variance, a significant underestimation bias arises. To minimize the underestimation, we introduce a parameter-free, novel deep Q-learning variant. Our Q-value update rule combines the notions behind Clipped Double Q-learning and Maxmin Q-learning by computing the critic objective through the nested combination of maximum and minimum operators to bound the approximate value estimates. We evaluate our modification on the suite of several OpenAI Gym continuous control tasks, improving the state-of-the-art in every environment tested.

PaperPDFCode

Code

baturaysaglam/TCD3 mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Continuous ControlDeep Reinforcement LearningOpenAI GymQ-LearningReinforcement Learning (RL)continuous-controlreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Clipped Double Q-learningDouble Q-learningQ-Learning

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections