English
Related papers

Related papers: Goal Misgeneralization in Deep Reinforcement Learn…

200 papers

Reinforcement Learning (RL) has become the de facto standard for tuning LLMs to solve tasks involving reasoning. However, growing evidence shows that models trained in such way often suffer from a significant loss in diversity. We argue…

Machine Learning · Computer Science 2026-03-09 Germán Kruszewski , Pierre Erbacher , Jos Rozen , Marc Dymetman

Model-based Reinforcement Learning (MBRL) aims to make agents more sample-efficient, adaptive, and explainable by learning an explicit model of the environment. While the capabilities of MBRL agents have significantly improved in recent…

Machine Learning · Computer Science 2024-04-09 Ran Wei , Nathan Lambert , Anthony McDonald , Alfredo Garcia , Roberto Calandra

Campbell-Goodhart's law relates to the causal inference error whereby decision-making agents aim to influence variables which are correlated to their goal objective but do not reliably cause it. This is a well known error in Economics and…

Machine Learning · Computer Science 2021-02-19 Hal Ashton

To date, distributional reinforcement learning (distributional RL) methods have exclusively focused on the discounted setting, where an agent aims to optimize a discounted sum of rewards over time. In this work, we extend distributional RL…

Machine Learning · Computer Science 2026-01-14 Juan Sebastian Rojas , Chi-Guhn Lee

Current reinforcement learning (RL) often suffers when solving a challenging exploration problem where the desired outcomes or high rewards are rarely observed. Even though curriculum RL, a framework that solves complex tasks by proposing a…

Machine Learning · Computer Science 2023-02-21 Daesol Cho , Seungjae Lee , H. Jin Kim

Reinforcement learning (RL) research focuses on general solutions that can be applied across different domains. This results in methods that RL practitioners can use in almost any domain. However, recent studies often lack the engineering…

Machine Learning · Computer Science 2021-07-05 Anssi Kanervisto , Christian Scheller , Yanick Schraner , Ville Hautamäki

Reinforcement Learning algorithms are primarily focused on learning a policy that maximizes expected return. As a result, the learned policy can exploit one or few reward sources. However, in many natural situations, it is desirable to…

Machine Learning · Computer Science 2026-03-31 Sagalpreet Singh , Rishi Saket , Aravindan Raghuveer

We introduce a new notion of generalization -- Distributional Generalization -- which roughly states that outputs of a classifier at train and test time are close *as distributions*, as opposed to close in just their average error. For…

Machine Learning · Computer Science 2020-10-16 Preetum Nakkiran , Yamini Bansal

The Overfitted Brain hypothesis suggests dreams happen to allow generalization in the human brain. Here, we ask if the same is true for reinforcement learning agents as well. Given limited experience in a real environment, we use…

Machine Learning · Computer Science 2024-03-14 Giorgio Franceschelli , Mirco Musolesi

One of the key reasons for the high sample complexity in reinforcement learning (RL) is the inability to transfer knowledge from one task to another. In standard multi-task RL settings, low-reward data collected while trying to solve one…

Machine Learning · Computer Science 2020-02-27 Alexander C. Li , Lerrel Pinto , Pieter Abbeel

Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause…

Robotics · Computer Science 2024-05-08 Yiwen Hou , Haoyuan Sun , Jinming Ma , Feng Wu

In this paper, we hypothesize that internal function sharing is one of the reasons to weaken o.o.d. or systematic generalization in deep learning for classification tasks. Under equivalent prediction, a model partitions an input space into…

Machine Learning · Computer Science 2022-08-25 Yuanpeng Li

Generalization remains a challenging problem for deep reinforcement learning algorithms, which are often trained and tested on the same set of deterministic game environments. When test environments are unseen and perturbed but the nature…

Machine Learning · Computer Science 2020-07-06 Jerry Zikun Chen

Most known regret bounds for reinforcement learning are either episodic or assume an environment without traps. We derive a regret bound without making either assumption, by allowing the algorithm to occasionally delegate an action to an…

Machine Learning · Computer Science 2019-07-22 Vanessa Kosoy

Continual learning (CL), which aims to learn a sequence of tasks, has attracted significant recent attention. However, most work has focused on the experimental performance of CL, and theoretical studies of CL are still limited. In…

Machine Learning · Computer Science 2023-02-14 Sen Lin , Peizhong Ju , Yingbin Liang , Ness Shroff

This work introduces a neuro-symbolic agent that combines deep reinforcement learning (DRL) with temporal logic (TL) to achieve systematic zero-shot, i.e., never-seen-before, generalisation of formally specified instructions. In particular,…

Machine Learning · Computer Science 2021-09-14 Borja G. León , Murray Shanahan , Francesco Belardinelli

In Multi-Goal Reinforcement Learning, an agent learns to achieve multiple goals with a goal-conditioned policy. During learning, the agent first collects the trajectories into a replay buffer, and later these trajectories are selected…

Machine Learning · Computer Science 2020-05-26 Rui Zhao , Xudong Sun , Volker Tresp

To achieve general intelligence, agents must learn how to interact with others in a shared environment: this is the challenge of multiagent reinforcement learning (MARL). The simplest form is independent reinforcement learning (InRL), where…

Artificial Intelligence · Computer Science 2017-11-08 Marc Lanctot , Vinicius Zambaldi , Audrunas Gruslys , Angeliki Lazaridou , Karl Tuyls , Julien Perolat , David Silver , Thore Graepel

In this lecture, we present a general perspective on reinforcement learning (RL) objectives, where we show three versions of objectives. The first version is the standard definition of objective in RL literature. Then we extend the standard…

Machine Learning · Computer Science 2023-06-06 Long Yang

Reinforcement Learning (RL) based solutions are being adopted in a variety of domains including robotics, health care and industrial automation. Most focus is given to when these solutions work well, but they fail when presented with out of…

Machine Learning · Computer Science 2021-12-07 Aaqib Parvez Mohammed , Matias Valdenegro-Toro