DOMINO: Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning
Yao Mu, Yuzheng Zhuang, Fei Ni, Bin Wang, Jianyu Chen, Jianye Hao, Ping Luo
2022Year
15Citations
9Top-tier citations
Abstract
According to the Barber and Agakov's variational lower bound [1], the mutual information I(x; y) between x and y can be bounded as follows:
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 3219932e-49f6-4879-9655-e89945f3c14dCited by top-tier papers9
- MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RLFei Ni, Jianye Hao, Yao Mu, Yifu Yuan et al.ICML 2023 · 75 citations
- ODE-based Recurrent Model-free Reinforcement Learning for POMDPsXuanle Zhao, Duzhen Zhang, Liyuan Han, Tielin Zhang et al.NeurIPS 2023 · 18 citations
- Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot GeneralizationFrank Röder, Jan Benad, Manfred Eppe, Pradeep Kr. BanerjeeNeurIPS 2025 · 9 citations
- Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement LearningXuehui Yu, Mhairi Dunion, Xin Li, Stefano V. AlbrechtNeurIPS 2024 · 6 citations
- MetaCARD: Meta-Reinforcement Learning with Task Uncertainty Feedback via Decoupled Context-Aware Reward and Dynamics ComponentsMin Wang, Xin Li, Leiji Zhang, Mingzhong WangAAAI 2024 · 6 citations
Builds on3
- Context-aware Dynamics Model for Generalization in Model-Based Reinforcement LearningKimin Lee, Younggyo Seo, Seunghyun Lee, Honglak Lee et al.ICML 2020 · 158 citations
- Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement LearningYounggyo Seo, Kimin Lee, Ignasi Clavera Gilaberte, Thanard Kurutach et al.NeurIPS 2020 · 51 citations
- A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement LearningJiaxian Guo, Mingming Gong, Dacheng TaoICLR 2022 · 21 citations
Related papers
- Connecting Jensen-Shannon and Kullback-Leibler Divergences: A New Bound for Representation LearningReuben Dorent, Polina Golland, William (Sandy) WellsNeurIPS 2025 · 7 citations
- Improving Mutual Information Estimation with Annealed and Energy-Based BoundsRob Brekelmans, Sicong Huang, Marzyeh Ghassemi, Greg Ver Steeg et al.ICLR 2022 · 16 citations
- Understanding the Limitations of Variational Mutual Information EstimatorsJiaming Song, Stefano ErmonICLR 2020 · 243 citations
- Sequential and Parallel Constrained Max-value Entropy Search via Information Lower BoundShion Takeno, Tomoyuki Tamura, Kazuki Shitara, Masayuki KarasuyamaICML 2022 · 27 citations
- Mutual Information Estimation via f-Divergence and Data DerangementsNunzio Alexandro Letizia, Nicola Novello, Andrea M. TonelloNeurIPS 2024 · 26 citations
