English
Related papers

Related papers: Improving Zero-shot Generalization in Offline Rein…

200 papers

We consider the problem of generalization in reinforcement learning where visual aspects of the observations might differ, e.g. when there are different backgrounds or change in contrast, brightness, etc. We assume that our agent has access…

Machine Learning · Computer Science 2021-02-16 Bonnie Li , Vincent François-Lavet , Thang Doan , Joelle Pineau

Generalization in Reinforcement Learning (RL) aims to learn an agent during training that generalizes to the target environment. This paper studies RL generalization from a theoretical aspect: how much can we expect pre-training over…

Machine Learning · Computer Science 2023-06-30 Haotian Ye , Xiaoyu Chen , Liwei Wang , Simon S. Du

As a step towards developing zero-shot task generalization capabilities in reinforcement learning (RL), we introduce a new RL problem where the agent should learn to execute sequences of instructions after learning useful skills that solve…

Artificial Intelligence · Computer Science 2017-11-08 Junhyuk Oh , Satinder Singh , Honglak Lee , Pushmeet Kohli

In this work, we address the challenge of zero-shot generalization (ZSG) in Reinforcement Learning (RL), where agents must adapt to entirely novel environments without additional training. We argue that understanding and utilizing…

Machine Learning · Computer Science 2024-04-16 Tidiane Camaret Ndir , André Biedenkapp , Noor Awad

Supervised fine-tuning (SFT) and reinforcement learning (RL) are widely used post-training techniques for foundation models. However, their roles in enhancing model generalization capabilities remain unclear. This paper studies the…

Artificial Intelligence · Computer Science 2025-05-27 Tianzhe Chu , Yuexiang Zhai , Jihan Yang , Shengbang Tong , Saining Xie , Dale Schuurmans , Quoc V. Le , Sergey Levine , Yi Ma

Over the past few years, the acceleration of computing resources and research in deep learning has led to significant practical successes in a range of tasks, including in particular in computer vision. Building on these advances,…

Artificial Intelligence · Computer Science 2022-04-14 David Bertoin , Emmanuel Rachelson

Reinforcement learning (RL)-based post-training often improves the reasoning performance of large language models (LLMs) beyond the training domain, while supervised fine-tuning (SFT) frequently leads to general capabilities forgetting.…

Computation and Language · Computer Science 2026-04-29 Dan Shi , Zhuowen Han , Simon Ostermann , Renren Jin , Josef van Genabith , Deyi Xiong

Query-focused Summarization (QfS) deals with systems that generate summaries from document(s) based on a query. Motivated by the insight that Reinforcement Learning (RL) provides a generalization to Supervised Learning (SL) for Natural…

Computation and Language · Computer Science 2023-11-30 Swaroop Nath , Harshad Khadilkar , Pushpak Bhattacharyya

A fundamental trait of intelligence is the ability to achieve goals in the face of novel circumstances, such as making decisions from new action choices. However, standard reinforcement learning assumes a fixed set of actions and requires…

Machine Learning · Computer Science 2020-11-04 Ayush Jain , Andrew Szot , Joseph J. Lim

Modern reinforcement learning (RL) systems capture deep truths about general, human problem-solving. In domains where new data can be simulated cheaply, these systems uncover sequential decision-making policies that far exceed the ability…

Machine Learning · Computer Science 2025-10-07 Scott Jeen

Recent advancements in zero-shot reinforcement learning (RL) have facilitated the extraction of diverse behaviors from unlabeled, offline data sources. In particular, forward-backward algorithms (FB) can retrieve a family of policies that…

Machine Learning · Computer Science 2026-02-09 Marco Bagatella , Thomas Rupf , Georg Martius , Andreas Krause

In Reinforcement Learning (RL), training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration. Recently, offline RL provides a promising solution by giving an initialized offline…

Machine Learning · Computer Science 2024-05-14 Changhong Wang , Xudong Yu , Chenjia Bai , Qiaosheng Zhang , Zhen Wang

Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is…

Machine Learning · Computer Science 2025-05-20 Yi Zhao , Aidan Scannell , Wenshuai Zhao , Yuxin Hou , Tianyu Cui , Le Chen , Dieter Büchler , Arno Solin , Juho Kannala , Joni Pajarinen

Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these…

Robotics · Computer Science 2024-03-05 Chenyang Cao , Zichen Yan , Renhao Lu , Junbo Tan , Xueqian Wang

In reinforcement learning (RL), key components of many algorithms are the exploration strategy and replay buffer. These strategies regulate what environment data is collected and trained on and have been extensively studied in the RL…

Machine Learning · Computer Science 2023-09-01 Max Weltevrede , Matthijs T. J. Spaan , Wendelin Böhmer

In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training. Distributionally robust reinforcement learning (DR-RL)…

Machine Learning · Computer Science 2026-03-05 Debamita Ghosh , George K. Atia , Yue Wang

Unsupervised and self-supervised objectives, such as next token prediction, have enabled pre-training generalist models from large amounts of unlabeled data. In reinforcement learning (RL), however, finding a truly general and scalable…

Machine Learning · Computer Science 2024-05-28 Seohong Park , Tobias Kreiman , Sergey Levine

Offline Reinforcement Learning (RL) provides a promising avenue for training policies from pre-collected datasets when gathering additional interaction data is infeasible. However, existing offline RL methods often assume stationarity or…

Machine Learning · Computer Science 2025-12-30 Suzan Ece Ada , Georg Martius , Emre Ugur , Erhan Oztop

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Qiyang Li , Sergey Levine

We introduce a method to address goal misgeneralization in reinforcement learning (RL), leveraging Large Language Model (LLM) feedback during training. Goal misgeneralization, a type of robustness failure in RL occurs when an agent retains…

Machine Learning · Computer Science 2024-01-17 Houda Nait El Barj , Theophile Sautory