English
Related papers

Related papers: Cyclic Policy Distillation: Sample-Efficient Sim-t…

200 papers

We present a framework for robot skill acquisition, which 1) efficiently scale up data generation of language-labelled robot data and 2) effectively distills this data down into a robust multi-task language-conditioned visuo-motor policy.…

Robotics · Computer Science 2023-10-03 Huy Ha , Pete Florence , Shuran Song

Transferring learned skills across diverse situations remains a fundamental challenge for autonomous agents, particularly when agents are not allowed to interact with an exact target setup. While prior approaches have predominantly focused…

Machine Learning · Computer Science 2024-07-25 Hayato Watahiki , Ryo Iwase , Ryosuke Unno , Yoshimasa Tsuruoka

Transfer reinforcement learning aims to improve the sample efficiency of solving unseen new tasks by leveraging experiences obtained from previous tasks. We consider the setting where all tasks (MDPs) share the same environment dynamic…

Machine Learning · Computer Science 2021-01-08 Kaige Yang

Existing methods for distillation do not efficiently utilize the training data. This work presents a novel approach to perform distillation using only a subset of the training data, making it more data-efficient. For this purpose, the…

Machine Learning · Computer Science 2021-04-26 Sourav Mishra , Suresh Sundaram

Pretrained foundation models have exhibited extraordinary in-context learning performance, allowing zero-shot generalization to new tasks not encountered during pretraining. In the case of reinforcement learning (RL), in-context RL (ICRL)…

Machine Learning · Computer Science 2025-05-05 Weiqin Chen , Santiago Paternain

We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning. The core idea is to consider the predictions of a source domain network on target domain data as noisy labels, and learn a…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Yash Patel , Kashyap Chitta , Bhavan Jasani

Cross-domain imitation learning (CDIL) accelerates policy learning by transferring expert knowledge across domains, which is valuable in applications where the collection of expert data is costly. Existing methods are either supervised,…

Machine Learning · Computer Science 2026-02-12 Li-Min Chu , Kai-Siang Ma , Ming-Hong Chen , Ping-Chun Hsieh

Today's advanced Reinforcement Learning algorithms produce black-box policies, that are often difficult to interpret and trust for a person. We introduce a policy distilling algorithm, building on the CN2 rule mining algorithm, that…

Artificial Intelligence · Computer Science 2021-06-14 Youri Coppens , Denis Steckelmacher , Catholijn M. Jonker , Ann Nowé

Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually considered despite its…

Robotics · Computer Science 2021-11-02 Alex Church , John Lloyd , Raia Hadsell , Nathan F. Lepora

We present differentiable predictive control (DPC), a method for learning constrained neural control policies for linear systems with probabilistic performance guarantees. We employ automatic differentiation to obtain direct policy…

Systems and Control · Electrical Eng. & Systems 2022-01-28 Jan Drgona , Aaron Tuor , Draguna Vrabie

Learning robot control policies from physics simulations is of great interest to the robotics community as it may render the learning process faster, cheaper, and safer by alleviating the need for expensive real-world experiments. However,…

Robotics · Computer Science 2021-06-22 Fabio Muratore , Michael Gienger , Jan Peters

Training a robust policy is critical for policy deployment in real-world systems or dealing with unknown dynamics mismatch in different dynamic systems. Domain Randomization~(DR) is a simple and elegant approach that trains a conservative…

Machine Learning · Computer Science 2023-05-23 Kang Xu , Yan Ma , Wei Li

Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a stochastic differential equation (SDE). However, the same…

Dexterous manipulation is physics-intensive and highly sensitive to modeling errors and perception noise, making sim-to-real transfer prohibitively challenging. Domain randomization (DR) is commonly used to improve the robustness of learned…

Robotics · Computer Science 2026-05-12 Kejia Ren , Gaotian Wang , Andrew S. Morgan , Kaiyu Hang

Despite the recent success of deep neural networks, there remains a need for effective methods to enhance domain generalization using vision transformers. In this paper, we propose a novel domain generalization technique called Robust…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Ankur Singh , Senthilnath Jayavelu

Continuous Integration and Continuous Deployment (CI/CD) pipelines are central to modern software delivery, yet their static workflows often introduce inefficiencies as systems scale. This paper proposes a reinforcement learning (RL) based…

This paper introduces two novel modifications to the Dynamic sAmpling Policy Optimization (DAPO) algorithm [1], approached from a mixed-policy perspective. Standard policy gradient methods can suffer from instability and sample…

Machine Learning · Computer Science 2025-08-20 Hongze Tan , Yuchen Li

Continual learning, enabling models to acquire new skills and knowledge without degrading existing capabilities, remains a fundamental challenge for foundation models. While on-policy reinforcement learning can reduce forgetting, it…

Machine Learning · Computer Science 2026-01-28 Idan Shenfeld , Mehul Damani , Jonas Hübotter , Pulkit Agrawal

Reinforcement learning (RL) is a powerful tool for finding optimal policies in sequential decision processes. However, deep RL methods have two weaknesses: collecting the amount of agent experience required for practical RL problems is…

Deep networks devour millions of precisely annotated images to build their complex and powerful representations. Unfortunately, tasks like autonomous driving have virtually no real-world training data. Repeatedly crashing a car into a tree…

Computer Vision and Pattern Recognition · Computer Science 2025-11-03 Brady Zhou , Nimit Kalra , Philipp Krähenbühl
‹ Prev 1 3 4 5 6 7 10 Next ›