Generalization in RL

RL: Reinforcement Learning

Overview

The field asks whether an agent can act effectively when goals, layouts, visual inputs, dynamics, or collaborators differ from training, a requirement for reliable deployment. Common approaches include domain randomization and exploration for broader state coverage, invariant or task-conditioned representations, meta-learning, curricula, reusable skills, and Bayesian or model-based transfer. Researchers evaluate these methods in settings such as Procgen, MuJoCo, MetaWorld, DeepMind Control, robotics, and language-based agents, using held-out tasks, environments, and visual or dynamics shifts. A central tension is that diversity and regularization can improve transfer but hinder learning or retention, while benchmark design and metrics can make apparent generalization gains hard to interpret.

Latest papers

CardsList

97 papers10 papers in the last four weeks, down 47% on the four weeks before. 0.1% of all new papers.

  1. KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

    Jan 20, 2026Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev +1RL BenchmarksReinforcement Learning

  2. Meta-RL with Bayesian Linear Task Models

    Dec 24, 2025Jingyang You, Hanna KurniawatiRepresentation LearningReinforcement Learning

  3. RAD: Retrieval High-quality Demonstrations to Enhance Decision-making

    Jul 21, 2025Lu Guo, Yixiang Shan, Zhengbang Zhu +5Offline RLGeneralization in RL

  4. Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making

    Apr 12, 2025Zhiyong WangMulti-Armed BanditsReinforcement Learning

  5. A Generalist Hanabi Agent

    Mar 17, 2025Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond +3RL for Game AICooperative MARL

  6. Training on Irrelevant States Implies Data Augmentation: Generalization in Contextual MDPs

    Oct 4, 2024Max Weltevrede, Caroline Horsch, Matthijs T. J. Spaan +1Reinforcement LearningRL Exploration

  7. Policy Learning with a Language Bottleneck

    May 7, 2024Megha Srivastava, Cedric Colas, Dorsa Sadigh +1Policy LearningLLM-Guided RL