English
Related papers

Related papers: Goal-conditioned Batch Reinforcement Learning for …

200 papers

Offline goal-conditioned reinforcement learning (GCRL) is a promising approach for pretraining generalist policies on large datasets of reward-free trajectories, akin to the self-supervised objectives used to train foundation models for…

Machine Learning · Computer Science 2026-01-05 John L. Zhou , Jonathan C. Kao

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Robotics · Computer Science 2019-02-15 Tianhe Yu , Gleb Shevchuk , Dorsa Sadigh , Chelsea Finn

In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled by a reward function. In applied settings such as video game…

Machine Learning · Computer Science 2025-06-30 Alessandro Sestini , Joakim Bergdahl , Konrad Tollmar , Andrew D. Bagdanov , Linus Gisslén

Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience can be acquired. This property makes these algorithms…

Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through…

Robotics · Computer Science 2017-11-23 Wenbin Li , Jeannette Bohg , Mario Fritz

Robotic navigation in environments shared with other robots or humans remains challenging because the intentions of the surrounding agents are not directly observable and the environment conditions are continuously changing. Local…

Robotics · Computer Science 2021-03-01 Bruno Brito , Michael Everett , Jonathan P. How , Javier Alonso-Mora

Reinforcement learning (RL) algorithms find applications in inventory control, recommender systems, vehicular traffic management, cloud computing and robotics. The real-world complications of many tasks arising in these domains makes them…

Machine Learning · Computer Science 2021-06-03 Sindhu Padakandla

Agents that can learn to imitate given video observation -- \emph{without direct access to state or action information} are more applicable to learning in the natural world. However, formulating a reinforcement learning (RL) agent that…

Machine Learning · Computer Science 2023-07-14 Glen Berseth , Florian Golemo , Christopher Pal

Humans have needs motivating their behavior according to intensity and context. However, we also create preferences associated with each action's perceived pleasure, which is susceptible to changes over time. This makes decision-making more…

Robotics · Computer Science 2024-09-05 Letícia Berto , Paula Costa , Alexandre Simões , Ricardo Gudwin , Esther Colombini

The pretraining-finetuning paradigm has facilitated numerous transformative advancements in artificial intelligence research in recent years. However, in the domain of reinforcement learning (RL) for robot locomotion, individual skills are…

Robotics · Computer Science 2026-03-10 Jiale Fan , Andrei Cramariuc , Tifanny Portela , Marco Hutter

While reinforcement learning provides an appealing formalism for learning individual skills, a general-purpose robotic system must be able to master an extensive repertoire of behaviors. Instead of learning a large collection of skills…

Robotics · Computer Science 2019-10-28 Ashvin Nair , Shikhar Bahl , Alexander Khazatsky , Vitchyr Pong , Glen Berseth , Sergey Levine

In this paper, we propose a novel approach for agent motion prediction in cluttered environments. One of the main challenges in predicting agent motion is accounting for location and context-specific information. Our main contribution is…

Robotics · Computer Science 2020-07-08 Igor Gilitschenski , Guy Rosman , Arjun Gupta , Sertac Karaman , Daniela Rus

We study goal-conditioned RL through the lens of generalization, but not in the traditional sense of random augmentations and domain randomization. Rather, we aim to learn goal-directed policies that generalize with respect to the horizon:…

Machine Learning · Computer Science 2025-01-29 Vivek Myers , Catherine Ji , Benjamin Eysenbach

Training reinforcement learning (RL) policies for legged locomotion often requires extensive environment interactions, which are costly and time-consuming. We propose Symmetry-Guided Memory Augmentation (SGMA), a framework that improves…

Machine Learning · Computer Science 2026-03-26 Kaixi Bao , Chenhao Li , Yarden As , Andreas Krause , Marco Hutter

Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the…

When performing tasks like laundry, humans naturally coordinate both hands to manipulate objects and anticipate how their actions will change the state of the clothes. However, achieving such coordination in robotics remains challenging due…

Robotics · Computer Science 2025-04-01 Haonan Chen , Jiaming Xu , Lily Sheng , Tianchen Ji , Shuijing Liu , Yunzhu Li , Katherine Driggs-Campbell

Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce Hyper-GoalNet, a framework that generates task-specific policy…

Robotics · Computer Science 2025-12-02 Pei Zhou , Wanting Yao , Qian Luo , Xunzhe Zhou , Yanchao Yang

We focus on the task of goal-oriented grasping, in which a robot is supposed to grasp a pre-assigned goal object in clutter and needs some pre-grasp actions such as pushes to enable stable grasps. However, in this task, the robot gets…

Robotics · Computer Science 2021-06-24 Kechun Xu , Hongxiang Yu , Qianen Lai , Yue Wang , Rong Xiong

Parkour is a grand challenge for legged locomotion that requires robots to overcome various obstacles rapidly in complex environments. Existing methods can generate either diverse but blind locomotion skills or vision-based but specialized…

Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitives, one of the limitations of existing methods is that the…

Robotics · Computer Science 2020-09-24 Takayuki Osa , Shuhei Ikemoto