中文
相关论文

相关论文: Forgetting and Imbalance in Robot Lifelong Learnin…

200 篇论文

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its…

机器学习 · 计算机科学 2023-10-18 Xiaohan Hu , Yi Ma , Chenjun Xiao , Yan Zheng , Jianye Hao

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and…

机器学习 · 计算机科学 2022-05-24 Hana Hoshino , Kei Ota , Asako Kanezaki , Rio Yokota

Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without interacting with the environment. A common challenge is handling multi-modal action distributions, where multiple behaviours are represented in…

机器学习 · 计算机科学 2025-03-20 Mianchu Wang , Yue Jin , Giovanni Montana

Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online RL agents trained in imperfect simulation environments can…

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

机器学习 · 计算机科学 2025-04-21 Han-Dong Lim , Donghwan Lee

Among the reasons hindering reinforcement learning (RL) applications to real-world problems, two factors are critical: limited data and the mismatch between the testing environment (real environment in which the policy is deployed) and the…

机器学习 · 计算机科学 2023-01-30 Xiaoteng Ma , Zhipeng Liang , Jose Blanchet , Mingwen Liu , Li Xia , Jiheng Zhang , Qianchuan Zhao , Zhengyuan Zhou

Offline reinforcement learning algorithms still lack trust in practice due to the risk that the learned policy performs worse than the original policy that generated the dataset or behaves in an unexpected way that is unfamiliar to the…

机器学习 · 计算机科学 2023-01-26 Phillip Swazinna , Steffen Udluft , Thomas Runkler

End-to-end learning robotic manipulation with high data efficiency is one of the key challenges in robotics. The latest methods that utilize human demonstration data and unsupervised representation learning has proven to be a promising…

机器人学 · 计算机科学 2021-10-22 Jin Li , Xianyuan Zhan , Zixu Xiao , Guyue Zhou

Robust control policy learning for autonomous driving requires training environments to be both physically realistic and computationally scalable, properties that existing simulators provide only in isolation. We introduce Sim2Sim2Sim, a…

机器人学 · 计算机科学 2026-05-05 Xunjiang Gu , Kashyap Chitta , Mahsa Golchoubian , Vladimir Suplin , Igor Gilitschenski

Continual Reinforcement Learning (CRL) aims to develop lifelong learning agents to continuously acquire knowledge across diverse tasks while mitigating catastrophic forgetting. This requires efficiently managing the stability-plasticity…

机器学习 · 计算机科学 2026-02-02 Yuxuan Li , Qijun He , Mingqi Yuan , Wen-Tse Chen , Jeff Schneider , Jiayu Chen

Recent advances in batch (offline) reinforcement learning have shown promising results in learning from available offline data and proved offline reinforcement learning to be an essential toolkit in learning control policies in a model-free…

机器学习 · 计算机科学 2022-12-19 Ashish Kumar , Ilya Kuzovkin

We present Residual Policy Learning (RPL): a simple method for improving nondifferentiable policies using model-free deep reinforcement learning. RPL thrives in complex robotic manipulation tasks where good but imperfect controllers are…

机器人学 · 计算机科学 2019-01-04 Tom Silver , Kelsey Allen , Josh Tenenbaum , Leslie Kaelbling

Online interactions with the environment to collect data samples for training a Reinforcement Learning (RL) agent is not always feasible due to economic and safety concerns. The goal of Offline Reinforcement Learning is to address this…

机器学习 · 计算机科学 2021-10-05 Chi Zhang , Sanmukh Rao Kuppannagari , Viktor K Prasanna

Learning from Observations (LfO) is a practical reinforcement learning scenario from which many applications can benefit through the reuse of incomplete resources. Compared to conventional imitation learning (IL), LfO is more challenging…

机器学习 · 计算机科学 2021-03-01 Zhuangdi Zhu , Kaixiang Lin , Bo Dai , Jiayu Zhou

Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments may differ. For instance, in control systems, the robot(s)…

机器学习 · 计算机科学 2022-10-25 Jean-Baptiste Gaya , Laure Soulier , Ludovic Denoyer

As Large Language Models (LLMs) continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become a central engineering problem, and knowledge distillation remains the dominant…

机器学习 · 计算机科学 2026-05-19 Mingyang Song , Mao Zheng

Learning robust driving policies from large-scale, real-world datasets is a central challenge in autonomous driving, as online data collection is often unsafe and impractical. While Behavioral Cloning (BC) offers a straightforward approach…

机器学习 · 计算机科学 2025-08-28 Antonio Guillen-Perez

Off-policy learning is a framework for evaluating and optimizing policies without deploying them, from data collected by another policy. Real-world environments are typically non-stationary and the offline learned policies should adapt to…

机器学习 · 计算机科学 2021-04-06 Joey Hong , Branislav Kveton , Manzil Zaheer , Yinlam Chow , Amr Ahmed

Offline Behavior Distillation (OBD), which condenses massive offline RL data into a compact synthetic behavioral dataset, offers a promising approach for efficient policy training and can be applied across various downstream RL tasks. In…

机器学习 · 计算机科学 2025-12-09 Shiye Lei , Zhihao Cheng , Dacheng Tao

The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents,…