paper-with-me

홈 › Papers

Emergence of In-Context Reinforcement Learning from Noise Distillation

2023-12-19 · Ilya Zisman, Vladislav Kurenkov, Alexander Nikulin, Viacheslav Sinii, Sergey Kolesnikov

Recently, extensive studies in Reinforcement Learning have been carried out on the ability of transformers to adapt in-context to various environments and tasks. Current in-context RL methods are limited by their strict requirements for data, which needs to be generated by RL agents or labeled with actions from an optimal policy. In order to address this prevalent problem, we propose AD$^\varepsilon$, a new data acquisition approach that enables in-context Reinforcement Learning from noise-induced curriculum. We show that it is viable to construct a synthetic noise injection curriculum which helps to obtain learning histories. Moreover, we experimentally demonstrate that it is possible to alleviate the need for generation using optimal policies, with in-context RL still able to outperform the best suboptimal policy in a learning dataset by a 2x margin.

📄 PDF Abstract BibTeX arXiv:2312.12275

Code (1)

corl-team/ad-eps 공식 구현 pytorch

Tasks

In-Context Reinforcement Learningreinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Representation Convergence: Mutual Distillation is Secretly a Form of Regularization

2025-01-05 · Zhengpeng Xie, Jiahang Cao, Qiang Zhang, Jianxiong Zhang 외

In this paper, we argue that mutual distillation between reinforcement learning policies serves as an implicit regularization, preventing them from overfitting to irrelevant features. We highlight two key contributions: …

Deep Reinforcement LearningFormreinforcement-learningReinforcement Learning+3

GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language Models

2026-05-28 · Xiaohang Tang, Keyue Jiang, Che Liu, Qifang Zhao 외 arxiv

Reinforcement learning (RL) can be used to improve the policy (denoiser) of diffusion large language models (dLLMs), while being hindered by the intractability of the policy likelihood. A dominant and efficient family of…

Reinforcement Learning

In-context Reinforcement Learning with Algorithm Distillation

2022-10-25 · Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto 외

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats…

In-Context Reinforcement Learningreinforcement-learningReinforcement Learning

TED: Training-Free Experience Distillation for Multimodal Reasoning

2026-03-25 · Shuozhi Yuan, Jinqing Wang, Zihao Liu, Miaomiao Yuan 외 arxiv

Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeat…

Knowledge DistillationMultimodal Reasoning

Convergence and Emergence of In-Context Reinforcement Learning with Chain of Thought

2026-05-08 · Zixuan Xie, Xinyu Liu, Rohan Chandra, Shangtong Zhang arxiv

In-context reinforcement learning (ICRL) refers to the ability of RL agents to adapt to new tasks at inference time without parameter updates by conditioning on additional context. Recent empirical studies further demons…

Reinforcement Learning