method · first seen 19 Oct 2026
truncated quantile critics
Also: TQC
A off-policy actor-critic reinforcement learning algorithm that truncates the upper tail of a distributional critic to reduce overestimation.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Reinforcement Learning Controllers for Fusion Scenario DevelopmentPapers · 19 Oct 2026 · Evgeny Adishchev, Maxim Nurgaliev, Dmitry Sorokin, Alexander Granovsky, Maksim S…
- Enhancing Deep Reinforcement Learning for Robotic Motion Planning via Task DecompositionPapers · 26 Oct 2026 · Yuanzhi He, Victor Romero-Cano, Jiayu Xu, Juan David Hernández, Gualtiero Colom…
- Max-Min Throughput in RSMA-Aided SWIPT for Sustainable Internet of Underground Things: A Deep Reinforcement Learning ApproachPapers · 15 Nov 2026 · Kaiqiang Lin, Mohamed-Slim Alouini
Latest sources
- Max-Min Throughput in RSMA-Aided SWIPT for Sustainable Internet of Underground Things: A Deep Reinforcement Learning ApproachPapers · 15 Nov 2026 · Kaiqiang Lin, Mohamed-Slim Alouini
- Enhancing Deep Reinforcement Learning for Robotic Motion Planning via Task DecompositionPapers · 26 Oct 2026 · Yuanzhi He, Victor Romero-Cano, Jiayu Xu, Juan David Hernández, Gualtiero Colom…
- Reinforcement Learning Controllers for Fusion Scenario DevelopmentPapers · 19 Oct 2026 · Evgeny Adishchev, Maxim Nurgaliev, Dmitry Sorokin, Alexander Granovsky, Maksim S…