中文
相关论文

相关论文: Reward-free World Models for Online Imitation Lear…

200 篇论文

World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios like autonomous driving, noncontrollable dynamics that are independent or sparsely dependent on action signals often exist,…

机器学习 · 计算机科学 2023-11-20 Minting Pan , Xiangming Zhu , Yitao Zheng , Yunbo Wang , Xiaokang Yang

Inverse reinforcement learning has proved its ability to explain state-action trajectories of expert agents by recovering their underlying reward functions in increasingly challenging environments. Recent advances in adversarial learning…

机器学习 · 计算机科学 2019-12-10 Jacobo Roa-Vicens , Yuanbo Wang , Virgile Mison , Yarin Gal , Ricardo Silva

Reinforcement learning algorithms typically utilize an interactive simulator (i.e., environment) with a predefined reward function for policy training. Developing such simulators and manually defining reward functions, however, is often…

机器学习 · 计算机科学 2026-03-26 Woo-Jin Ahn , Sang-Ryul Baek , Yong-Jun Lee , Hyun-Duck Choi , Myo-Taeg Lim

Reinforcement learning (RL) is an appealing paradigm for training intelligent agents, enabling policy acquisition from the agent's own autonomously acquired experience. However, the training process of RL is far from automatic, requiring…

人工智能 · 计算机科学 2025-02-25 Zhao Yang , Thomas M. Moerland , Mike Preuss , Aske Plaat , Edward S. Hu

We apply reinforcement learning (RL) to robotics tasks. One of the drawbacks of traditional RL algorithms has been their poor sample efficiency. One approach to improve the sample efficiency is model-based RL. In our model-based RL…

机器学习 · 计算机科学 2023-05-16 Adithya Ramesh , Balaraman Ravindran

Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable…

机器学习 · 计算机科学 2019-03-11 Vaibhav Saxena , Srinivasan Sivanandan , Pulkit Mathur

Pretraining reinforcement learning (RL) models on offline datasets is a promising way to improve their training efficiency in online tasks, but challenging due to the inherent mismatch in dynamics and behaviors across various tasks. We…

机器学习 · 计算机科学 2024-06-06 Minting Pan , Yitao Zheng , Yunbo Wang , Xiaokang Yang

The aim of multi-task reinforcement learning is two-fold: (1) efficiently learn by training against multiple tasks and (2) quickly adapt, using limited samples, to a variety of new tasks. In this work, the tasks correspond to reward…

机器学习 · 计算机科学 2019-11-05 Nicholas C. Landolfi , Garrett Thomas , Tengyu Ma

Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational…

机器学习 · 计算机科学 2024-01-31 Gokul Swamy , Sanjiban Choudhury , J. Andrew Bagnell , Zhiwei Steven Wu

This work presents a case study of a learning-based approach for target driven map-less navigation. The underlying navigation model is an end-to-end neural network which is trained using a combination of expert demonstrations, imitation…

机器人学 · 计算机科学 2018-09-03 Mark Pfeiffer , Samarth Shukla , Matteo Turchetta , Cesar Cadena , Andreas Krause , Roland Siegwart , Juan Nieto

Many manipulation tasks require robots to interact with unknown environments. In such applications, the ability to adapt the impedance according to different task phases and environment constraints is crucial for safety and performance.…

机器人学 · 计算机科学 2021-02-16 Xiang Zhang , Liting Sun , Zhian Kuang , Masayoshi Tomizuka

Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment. These methods are sample efficient and facilitate learning in the real world but fail to generalize to subtle variations in the…

机器学习 · 计算机科学 2018-12-11 Christian F. Perez , Felipe Petroski Such , Theofanis Karaletsos

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…

机器学习 · 计算机科学 2023-11-02 Udaya Ghai , Arushi Gupta , Wenhan Xia , Karan Singh , Elad Hazan

Learning task-agnostic dynamics models in high-dimensional observation spaces can be challenging for model-based RL agents. We propose a novel way to learn latent world models by learning to predict sequences of future actions conditioned…

机器学习 · 计算机科学 2020-12-07 Keiran Paster , Sheila A. McIlraith , Jimmy Ba

In offline Imitation Learning (IL), one of the main challenges is the \textit{covariate shift} between the expert observations and the actual distribution encountered by the agent, because it is difficult to determine what action an agent…

机器学习 · 计算机科学 2024-06-19 Jie-Jing Shao , Hao-Sen Shi , Lan-Zhe Guo , Yu-Feng Li

Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer…

机器学习 · 计算机科学 2019-09-27 Siddharth Reddy , Anca D. Dragan , Sergey Levine

Imitation learning in a high-dimensional environment is challenging. Most inverse reinforcement learning (IRL) methods fail to outperform the demonstrator in such a high-dimensional environment, e.g., Atari domain. To address this…

机器学习 · 计算机科学 2020-09-14 Xingrui Yu , Yueming Lyu , Ivor W. Tsang

Offline reinforcement learning (RL) offers a powerful paradigm for data-driven control. Compared to model-free approaches, offline model-based RL (MBRL) explicitly learns a world model from a static dataset and uses it as a surrogate…

机器学习 · 计算机科学 2026-02-02 Jiayu Chen , Le Xu , Aravind Venugopal , Jeff Schneider

Humans are masters at quickly learning many complex tasks, relying on an approximate understanding of the dynamics of their environments. In much the same way, we would like our learning agents to quickly adapt to new tasks. In this paper,…

Imitation learning is an effective alternative approach to learn a policy when the reward function is sparse. In this paper, we consider a challenging setting where an agent and an expert use different actions from each other. We assume…

机器学习 · 计算机科学 2019-08-27 Konrad Zolna , Negar Rostamzadeh , Yoshua Bengio , Sungjin Ahn , Pedro O. Pinheiro