paper-with-me

Papers

Task diversity produces systematic transfer but inhibits continual reinforcement learning

2026-05-30 · Purab Seth, Neil Shah, Kunal Jha, Samuel J. Gershman, Max Kleiman-Weiner, Wilka Carvalho arxiv

Continual reinforcement learning aims to produce agents that learn not only to improve at their current tasks but also to adapt as task distributions change. Training an agent on many diverse tasks can induce zero-shot generalization, but previous work generally evaluates this generalization after training -- with frozen weights. Whether task diversity also improves an agent's ability to continue learning across distribution shifts remains unclear. We introduce Banyan, a GPU-accelerated continual RL domain in which task diversity factors into three independently controllable axes: the map layouts an agent must navigate, the objects it must interact with, and the hierarchical structures of sub-goal dependencies. Across individual distribution shifts, increasing diversity along each axis causes agents to begin training on the new tasks near the performance attained on the previous one, even when the shift changes the structure of the optimal policy. However, as the number of shifts increases, this local transfer does not by itself yield sustained continual learning: longer-horizon tasks plateau, and earlier task distributions are forgotten after later training. Banyan is a benchmark for studying when controlled task diversity produces transferable learning, when that transfer persists, and where it falls short of proper continual learning.

📄 PDF Abstract BibTeX arXiv:2606.00880

Code (0)

등록된 구현이 없습니다.

Tasks

Zero-shot GeneralizationReinforcement LearningContinual Learning

Similar Papers 제목 키워드 기반

Quality Diversity for Visual Pre-Training

2023-01-01 · ICCV 2023 1 · Ruchika Chavhan, Henry Gouk, Da Li, Timothy Hospedales

Models pre-trained on large datasets such as ImageNet provide the de-facto standard for transfer learning, with both supervised and self-supervised approaches proving effective. However, emerging evidence suggests th…

DiversityInductive BiasTransfer Learning

The impact of data set similarity and diversity on transfer learning success in time series forecasting

2024-04-09 · Claudia Ehrig, Benedikt Sonnleitner, Ursula Neumann, Catherine Cleophas 외

Pre-trained models have become pivotal in enhancing the efficiency and accuracy of time series forecasting on target data sets by leveraging transfer learning. While benchmarks validate the performance of model generaliz…

DiversityTime SeriesTime Series ForecastingTransfer Learning

Empirical Evaluation of Supervision Signals for Style Transfer Models

2021-01-15 · Yevgeniy Puzikov, Simoes Stanley, Iryna Gurevych, Immanuel Schweizer

Text style transfer has gained increasing attention from the research community over the recent years. However, the proposed approaches vary in many ways, which makes it hard to assess the individual contribution of the …

Machine Translationreinforcement-learningReinforcement LearningReinforcement Learning (RL)+3

Data Analogies Enable Efficient Cross-Embodiment Transfer

2026-03-06 · Jonathan Yang, Chelsea Finn, Dorsa Sadigh arxiv

Generalist robot policies are trained on demonstrations collected across a wide variety of robots, scenes, and viewpoints. Yet it remains unclear how to best organize and scale such heterogeneous data so that it genuinel…

Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation

2021-03-16 · CVPR 2021 1 · Jungbeom Lee, Eunji Kim, Sungroh Yoon

Weakly supervised semantic segmentation produces a pixel-level localization from a classifier, but it is likely to restrict its focus to a small discriminative region of the target object. AdvCAM is an attribution map of…

Adversarial AttackObjectSegmentationSemantic Segmentation+3