Maximum Total Correlation Reinforcement Learning
Bang You, Puze Liu, Huaping Liu, Jan Peters, Oleg Arenz
2025Year
Abstract
RPC LZ-SAC MTC (ours) SAC Action State Figure 1. Maximizing the total correlation within trajectories results in more consistent behavior. As shown in our experiments, this consistency increases robustness to noise and dynamics changes.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 32f09c4c-ff58-4f11-9f49-e510b503ee37Builds on18
- CURL: Contrastive Unsupervised Representations for Reinforcement LearningMichael Laskin, Aravind Srinivas, Pieter AbbeelICML 2020 · 1,261 citations
- Improving Sample Efficiency in Model-Free Reinforcement Learning from ImagesDenis Yarats, Amy Zhang, Ilya Kostrikov, Brandon Amos et al.AAAI 2021 · 506 citations
- Temporal Difference Learning for Model Predictive ControlNicklas Hansen, Hao Su, Xiaolong WangICML 2022 · 388 citations
- Deep Reinforcement and InfoMax LearningBogdan Mazoure, Remi Tachet des Combes, Thang Doan, Philip Bachman et al.NeurIPS 2020 · 118 citations
- BYOL-Explore: Exploration by Bootstrapped PredictionZhaohan Guo, Shantanu Thakoor, Miruna Pislar, Bernardo Ávila Pires et al.NeurIPS 2022 · 104 citations
Related papers
- Robust Situational Reinforcement Learning in Face of Context DisturbancesJinpeng Zhang, Yufeng Zheng, Chuheng Zhang, Li Zhao et al.ICML 2023 · 5 citations
- Latent exploration for Reinforcement LearningAlberto Silvio Chiappa, Alessandro Marin Vargas, Ann Zixiang Huang, Alexander MathisNeurIPS 2023 · 41 citations
- Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RLGuojian Zhan, Likun Wang, Pengcheng Wang, Feihong Zhang et al.ICML 2026
- Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution TrajectoriesLi-Cheng Lan, Huan Zhang, Cho-Jui HsiehICLR 2023 · 3 citations
- Dynamics Are Learned, Not Told: Semi-Supervised Discovery of Latent Dynamics Geometries For Zero-Shot Policy AdaptationZhiming Xu, Weitao Zhou, Xianghui Pan, Nanshan Deng et al.ICML 2026
