SQT -- std Q-target
Not on the map. Why?
Abstract (arXiv)
Std Q-target is a conservative, actor-critic, ensemble, Q-learning-based algorithm, which is based on a single key Q-formula: Q-networks standard deviation, which is an "uncertainty penalty", and, serves as a minimalistic solution to the problem of overestimation bias. We implement SQT on top of TD3/TD7 code and test it against the state-of-the-art (SOTA) actor-critic algorithms, DDPG, TD3 and TD7 on seven popular MuJoCo and Bullet tasks. Our results demonstrate SQT's Q-target formula superiority over TD3's Q-target formula as a conservative solution to overestimation bias in RL, while SQT shows a clear performance advantage on a wide margin over DDPG, TD3, and TD7 on all tasks.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 7 of its 19 references that are in the map. First posted on arXiv 3 Feb 2024.
Builds on
7 of 19 references.
References · 7
- 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
- 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
- 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
- 2021Randomized Ensembled Double Q-Learning: Learning Fast Without a Modelcited by 278
- 2020Maxmin Q-learning: Controlling the Estimation Bias of Q-learningcited by 117
- 2023For SALE: State-Action Representation Learning for Deep Reinforcement Learningcited by 73
- 2019Robust Temporal Difference Learning for Critical Domainscited by 7
Built on by
Not cited yet.