English
Related papers

Related papers: Offline Skill Generalization via Task and Motion P…

200 papers

Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics. Training individual policies for every single potential task is often impractical, especially for…

Machine Learning · Statistics 2014-02-13 Marc Peter Deisenroth , Peter Englert , Jan Peters , Dieter Fox

This paper presents an innovative method for humanoid robots to acquire a comprehensive set of motor skills through reinforcement learning. The approach utilizes an achievement-triggered multi-path reward function rooted in developmental…

Robotics · Computer Science 2023-11-14 Fanxing Meng , Jing Xiao

The learning efficiency and generalization ability of an intelligent agent can be greatly improved by utilizing a useful set of skills. However, the design of robot skills can often be intractable in real-world applications due to the…

Robotics · Computer Science 2021-06-29 Kuan Fang , Yuke Zhu , Silvio Savarese , Li Fei-Fei

Recent work has shown that complex manipulation skills, such as pushing or pouring, can be learned through state-of-the-art learning based techniques, such as Reinforcement Learning (RL). However, these methods often have high…

World models for environments with many objects face a combinatorial explosion of states: as the number of objects increases, the number of possible arrangements grows exponentially. In this paper, we learn to generalize over robotic…

Robotics · Computer Science 2022-02-14 Ondrej Biza , Thomas Kipf , David Klee , Robert Platt , Jan-Willem van de Meent , Lawson L. S. Wong

The Reinforcement Learning (RL) paradigm has been an essential tool for automating robotic tasks. Despite the advances in RL, it is still not widely adopted in the industry due to the need for an expensive large amount of robot interaction…

The offline reinforcement learning (RL) paradigm provides a general recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. While policy constraints, conservatism, and other…

Artificial Intelligence · Computer Science 2023-10-19 Jianlan Luo , Perry Dong , Jeffrey Wu , Aviral Kumar , Xinyang Geng , Sergey Levine

We study the problem of offline pre-training and online fine-tuning for reinforcement learning from high-dimensional observations in the context of realistic robot tasks. Recent offline model-free approaches successfully use online…

Machine Learning · Computer Science 2024-01-09 Rafael Rafailov , Kyle Hatch , Victor Kolev , John D. Martin , Mariano Phielipp , Chelsea Finn

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

Applying reinforcement learning to robotic systems poses a number of challenging problems. A key requirement is the ability to handle continuous state and action spaces while remaining within a limited time and resource budget.…

Machine Learning · Computer Science 2020-06-29 Benjamin van Niekerk , Andreas Damianou , Benjamin Rosman

Vision-based learning methods provide promise for robots to learn complex manipulation tasks. However, how to generalize the learned manipulation skills to real-world interactions remains an open question. In this work, we study robotic…

Robotics · Computer Science 2020-03-03 Zhixin Jia , Mengxiang Lin , Zhixin Chen , Shibo Jian

Reinforcement learning (RL) can automate a wide variety of robotic skills, but learning each new skill requires considerable real-world data collection and manual representation engineering to design policy classes or features. Using deep…

Machine Learning · Computer Science 2016-09-23 Coline Devin , Abhishek Gupta , Trevor Darrell , Pieter Abbeel , Sergey Levine

Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training…

Machine Learning · Statistics 2022-10-11 Shentao Yang , Zhendong Wang , Huangjie Zheng , Yihao Feng , Mingyuan Zhou

The training of autonomous agents often requires expensive and unsafe trial-and-error interactions with the environment. Nowadays several data sets containing recorded experiences of intelligent agents performing various tasks, spanning…

Machine Learning · Computer Science 2020-10-06 Giorgio Angelotti , Nicolas Drougard , Caroline Ponzoni Carvalho Chanel

Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization objective makes them computationally efficient and stable to…

Machine Learning · Computer Science 2025-12-30 Adam Jelley , Trevor McInroe , Sam Devlin , Amos Storkey

This article introduces the theory of offline reinforcement learning in large state spaces, where good policies are learned from historical data without online interactions with the environment. Key concepts introduced include expressivity…

Machine Learning · Computer Science 2025-10-07 Nan Jiang , Tengyang Xie

Humans demonstrate an impressive ability to acquire and generalize manipulation "tricks." Even from a single demonstration, such as using soup ladles to reach for distant objects, we can apply this skill to new scenarios involving different…

Robotics · Computer Science 2023-11-07 Jiayuan Mao , Joshua B. Tenenbaum , Tomás Lozano-Pérez , Leslie Pack Kaelbling

Robotic manipulation involves actions where contacts occur between the robot and the objects. In this scope, the availability of physics-based engines allows motion planners to comprise dynamics between rigid bodies, which is necessary for…

Robotics · Computer Science 2017-10-31 M Muhayyuddin , Aliakbar Akbari , Jan Rosell

Autonomous learning of robotic skills can allow general-purpose robots to learn wide behavioral repertoires without requiring extensive manual engineering. However, robotic skill learning methods typically make one of several trade-offs to…

Machine Learning · Computer Science 2016-10-07 William Montgomery , Anurag Ajay , Chelsea Finn , Pieter Abbeel , Sergey Levine

Deep reinforcement learning algorithms have succeeded in several challenging domains. Classic Online RL job schedulers can learn efficient scheduling strategies but often takes thousands of timesteps to explore the environment and adapt…

Machine Learning · Computer Science 2022-12-05 Vanamala Venkataswamy , Jake Grigsby , Andrew Grimshaw , Yanjun Qi