English
Related papers

Related papers: Learning Generalized Policies for Fully Observable…

200 papers

We consider the challenging problem of using domain knowledge to improve deep reinforcement learning policies. To this end, we propose LEGIBLE, a novel approach, following a multi-step process, which starts by mining rules from a deep RL…

Machine Learning · Computer Science 2025-03-13 Martin Tappler , Ignacio D. Lopez-Miguel , Sebastian Tschiatschek , Ezio Bartocci

Invariant approaches have been remarkably successful in tackling the problem of domain generalization, where the objective is to perform inference on data distributions different from those used in training. In our work, we investigate…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Abhimanyu Dubey , Vignesh Ramanathan , Alex Pentland , Dhruv Mahajan

Existing domain generalization aims to learn a generalizable model to perform well even on unseen domains. For many real-world machine learning applications, the data distribution often shifts gradually along domain indices. For example, a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-09 Qiuhao Zeng , Wei Wang , Fan Zhou , Charles Ling , Boyu Wang

In this paper we propose a method that learns to play Pac-Man. We define a set of high-level observation and action modules. Actions are temporally extended, and multiple action modules may be in effect concurrently. A decision of the agent…

Machine Learning · Computer Science 2007-05-23 Istvan Szita , Andras Lorincz

We introduce generalized filtration with which we can represent situations such as some agents forget information at some specific time. The filtration is defined as a functor to a category Prob whose objects are all probability spaces and…

Mathematical Finance · Quantitative Finance 2020-11-18 Takanori Adachi , Katsushi Nakajima , Yoshihiro Ryu

Goal-conditioned policies are generally understood to be "feed-forward" circuits, in the form of neural networks that map from the current state and the goal specification to the next action to take. However, under what circumstances such a…

Machine Learning · Computer Science 2024-05-06 Jiayuan Mao , Tomás Lozano-Pérez , Joshua B. Tenenbaum , Leslie Pack Kaelbling

Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for practitioners to express numerical preferences over…

The problem of domain generalization is to learn, given data from different source distributions, a model that can be expected to generalize well on new target distributions which are only seen through unlabeled samples. In this paper, we…

Machine Learning · Computer Science 2024-03-12 Markus Holzleitner , Sergei V. Pereverzyev , Werner Zellinger

Using LLMs not to predict plans but to formalize an environment into the Planning Domain Definition Language (PDDL) has been shown to improve performance and control. While most existing methodology only applies to fully observable…

Artificial Intelligence · Computer Science 2026-04-10 Liancheng Gong , Wang Zhu , Jesse Thomason , Li Zhang

Domain generalization (DG) is about learning models that generalize well to new domains that are related to, but different from, the training domain(s). It is a fundamental problem in machine learning and has attracted much attention in…

Machine Learning · Computer Science 2023-07-14 Nevin L. Zhang , Kaican Li , Han Gao , Weiyan Xie , Zhi Lin , Zhenguo Li , Luning Wang , Yongxiang Huang

Imitation learning is an effective and safe technique to train robot policies in the real world because it does not depend on an expensive random exploration process. However, due to the lack of exploration, learning policies that…

Robotics · Computer Science 2021-06-24 Ajay Mandlekar , Danfei Xu , Roberto Martín-Martín , Silvio Savarese , Li Fei-Fei

Guided policy search is a method for reinforcement learning that trains a general policy for accomplishing a given task by guiding the learning of the policy with multiple guiding distributions. Guided policy search relies on learning an…

Robotics · Computer Science 2017-10-03 Connor Schenck , Dieter Fox

For over three decades, the planning community has explored countless methods for data-driven model acquisition. These range in sophistication (e.g., simple set operations to full-blown reformulations), methodology (e.g., logic-based vs.…

Artificial Intelligence · Computer Science 2022-06-15 Ethan Callanan , Rebecca De Venezia , Victoria Armstrong , Alison Paredes , Tathagata Chakraborti , Christian Muise

Generalist imitation learning policies trained on large datasets show great promise for solving diverse manipulation tasks. However, to ensure generalization to different conditions, policies need to be trained with data collected across a…

In Environment Design, one interested party seeks to affect another agent's decisions by applying changes to the environment. Most research on planning environment (re)design assumes the interested party's objective is to facilitate the…

Artificial Intelligence · Computer Science 2024-02-15 Alberto Pozanco , Ramon Fraga Pereira , Daniel Borrajo

Diffusion-based policies have shown remarkable capability in executing complex robotic manipulation tasks but lack explicit characterization of geometry and semantics, which often limits their ability to generalize to unseen objects and…

Robotics · Computer Science 2024-10-24 Yixuan Wang , Guang Yin , Binghao Huang , Tarik Kelestemur , Jiuguang Wang , Yunzhu Li

Given data from diverse sets of distinct distributions, domain generalization aims to learn models that generalize to unseen distributions. A common approach is designing a data-driven surrogate penalty to capture generalization and…

Machine Learning · Computer Science 2023-08-31 Ozan Sener , Vladlen Koltun

Generalization in deep reinforcement learning over unseen environment variations usually requires policy learning over a large set of diverse training variations. We empirically observe that an agent trained on many variations (a…

Machine Learning · Computer Science 2022-06-28 Zhiwei Jia , Xuanlin Li , Zhan Ling , Shuang Liu , Yiran Wu , Hao Su

In this article, we work towards the goal of developing agents that can learn to act in complex worlds. We develop a probabilistic, relational planning rule representation that compactly models noisy, nondeterministic action effects, and…

Machine Learning · Computer Science 2011-10-12 L. P. Kaelbling , H. M. Pasula , L. S. Zettlemoyer

Reinforcement learning is a framework for learning to act sequentially in an unknown environment. We propose a natural approach for modeling policy structure in policy gradients. The key idea is to optimize for a subset of future rewards:…

Machine Learning · Computer Science 2026-03-09 Puneet Mathur , Branislav Kveton , Subhojyoti Mukherjee , Viet Dac Lai