paper-with-me

Papers

Vintix: Action Model via In-Context Reinforcement Learning

2025-01-31 · Andrey Polubarov, Nikita Lyubaykin, Alexander Derevyagin, Ilya Zisman, Denis Tarasov, Alexander Nikulin, Vladislav Kurenkov

In-Context Reinforcement Learning (ICRL) represents a promising paradigm for developing generalist agents that learn at inference time through trial-and-error interactions, analogous to how large language models adapt contextually, but with a focus on reward maximization. However, the scalability of ICRL beyond toy tasks and single-domain settings remains an open challenge. In this work, we present the first steps toward scaling ICRL by introducing a fixed, cross-domain model capable of learning behaviors through in-context reinforcement learning. Our results demonstrate that Algorithm Distillation, a framework designed to facilitate ICRL, offers a compelling and competitive alternative to expert distillation to construct versatile action models. These findings highlight the potential of ICRL as a scalable approach for generalist decision-making systems. Code to be released at https://github.com/dunnolab/vintix

📄 PDF Abstract BibTeX arXiv:2501.19400

Code (1)

dunnolab/vintix 공식 구현 pytorch

Tasks

Decision MakingIn-Context Reinforcement Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner

2026-04-06 · Andrei Polubarov, Lyubaykin Nikita, Alexander Derevyagin, Artyom Grishin 외 arxiv

Recent progress in in-context reinforcement learning (ICRL) has demonstrated its potential for training generalist agents that can acquire new tasks directly at inference. Algorithm Distillation (AD) pioneered this parad…

Reinforcement Learning

CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents

2026-07-06 · Yujiang Li, Zhenyu Hou, Yi Jing, Jie Tang 외 arxiv

Long-horizon agentic LLMs are increasingly limited by finite context windows, as extended interaction trajectories can exceed the maximum context length before a task is completed. Context compaction offers a natural sol…

Reinforcement Learning

A Survey of In-Context Reinforcement Learning

2025-02-11 · Amir Moeini, Jiuqi Wang, Jacob Beck, Ethan Blaser 외

Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new tasks without updating any parameters by…

In-Context Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1

Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments

2025-06-17 · Abhishek Verma, Nallarasan V, Balaraman Ravindran

Deep Reinforcement Learning (DRL) has achieved remarkable success in complex sequential decision-making tasks, such as playing Atari 2600 games and mastering board games. A critical yet underexplored aspect of DRL is the…

Atari GamesBoard GamesComputational EfficiencyDecision Making+6

In-Context Reinforcement Learning for Variable Action Spaces

2023-12-20 · Viacheslav Sinii, Alexander Nikulin, Vladislav Kurenkov, Ilya Zisman 외

Recently, it has been shown that transformers pre-trained on diverse datasets with multi-episode contexts can generalize to new reinforcement learning tasks in-context. A key limitation of previously proposed models is t…

In-Context Reinforcement LearningMulti-Armed Banditsreinforcement-learningReinforcement Learning