中文
相关论文

相关论文: Occupancy Reward Shaping: Improving Credit Assignm…

200 篇论文

Model-based offline optimization with dynamics-aware policy provides a new perspective for policy learning and out-of-distribution generalization, where the learned policy could adapt to different dynamics enumerated at the training stage.…

机器学习 · 计算机科学 2022-06-09 Chengxing Jia , Hao Yin , Chenxiao Gao , Tian Xu , Lei Yuan , Zongzhang Zhang , Yang Yu

We investigate the effect of reward shaping in improving the performance of reinforcement learning in the context of the real-time strategy, capture-the-flag game. The game is characterized by sparse rewards that are associated with…

机器学习 · 计算机科学 2023-11-29 John Kliem , Prithviraj Dasgupta

Real-time control for robotics is a popular research area in the reinforcement learning community. Through the use of techniques such as reward shaping, researchers have managed to train online agents across a multitude of domains. Despite…

机器人学 · 计算机科学 2023-04-21 Mihai Anca , Jonathan D. Thomas , Dabal Pedamonti , Matthew Studley , Mark Hansen

Developing agents that can execute multiple skills by learning from pre-collected datasets is an important problem in robotics, where online interaction with the environment is extremely time-consuming. Moreover, manually designing reward…

机器人学 · 计算机科学 2023-01-06 Lina Mezghani , Sainbayar Sukhbaatar , Piotr Bojanowski , Alessandro Lazaric , Karteek Alahari

Offline Safe Reinforcement Learning (OSRL) aims to learn a policy to achieve high performance in sequential decision-making while satisfying constraints, using only pre-collected datasets. Recent works, inspired by the strong capabilities…

机器学习 · 计算机科学 2026-02-06 Zifan Liu , Xinran Li , Shibo Chen , Jun Zhang

Offline reinforcement learning (RL) enables policy learning from pre-collected datasets, avoiding costly and risky online interactions, but it often struggles with long-horizon tasks involving sparse rewards. Existing goal-conditioned and…

机器学习 · 计算机科学 2026-01-14 Chengyang Gu , Yuxin Pan , Hui Xiong , Yize Chen

Most Reinforcement Learning (RL) methods are traditionally studied in an active learning setting, where agents directly interact with their environments, observe action outcomes, and learn through trial and error. However, allowing…

人工智能 · 计算机科学 2023-10-16 Maryam Zare , Parham M. Kebria , Abbas Khosravi

Effective exploration in reinforcement learning requires not only tracking where an agent has been, but also understanding how the agent perceives and represents the world. To learn powerful representations, an agent should actively explore…

机器学习 · 计算机科学 2026-04-21 Faisal Mohamed , Catherine Ji , Benjamin Eysenbach , Glen Berseth

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…

机器人学 · 计算机科学 2021-06-24 Kechun Xu , Hongxiang Yu , Qianen Lai , Yue Wang , Rong Xiong

Offline Reinforcement learning (RL) has shown potent in many safe-critical tasks in robotics where exploration is risky and expensive. However, it still struggles to acquire skills in temporally extended tasks. In this paper, we study the…

机器人学 · 计算机科学 2022-05-25 Jinning Li , Chen Tang , Masayoshi Tomizuka , Wei Zhan

Offline goal-conditioned reinforcement learning (GCRL) often struggles with long-horizon tasks, where errors in value estimation accumulate and produce unreliable policies. It is typically assumed that effective long-term planning is…

机器学习 · 计算机科学 2026-05-26 Evgenii Opryshko , Junwei Quan , Claas Voelcker , Yilun Du , Igor Gilitschenski

As a novel 3D scene representation, semantic occupancy has gained much attention in autonomous driving. However, existing occupancy prediction methods mainly focus on designing better occupancy representations, such as tri-perspective view…

计算机视觉与模式识别 · 计算机科学 2024-10-16 Zhiwei Lin , Hongbo Jin , Yongtao Wang , Yufei Wei , Nan Dong

Artificial Intelligence has been used to help human complete difficult tasks in complicated environments by providing optimized strategies for decision-making or replacing the manual labour. In environments including multiple agents, such…

机器学习 · 计算机科学 2023-07-24 Chaoyi Gu , Varuna De Silva , Corentin Artaud , Rafael Pina

Reinforcement learning, which acquires a policy maximizing long-term rewards, has been actively studied. Unfortunately, this learning type is too slow and difficult to use in practical situations because the state-action space becomes huge…

机器学习 · 计算机科学 2024-10-28 Takato Okudo , Seiji Yamada

State-of-the-art navigation methods leverage a spatial memory to generalize to new environments, but their occupancy maps are limited to capturing the geometric structures directly observed by the agent. We propose occupancy anticipation,…

计算机视觉与模式识别 · 计算机科学 2020-08-26 Santhosh K. Ramakrishnan , Ziad Al-Halah , Kristen Grauman

To promote cooperation in Multi-Agent Reinforcement Learning, the reward signals of all agents can be aggregated together, forming global rewards that are commonly known as the fully cooperative setting. However, global rewards are usually…

机器学习 · 计算机科学 2026-01-30 Bang Giang Le , Viet Cuong Ta

The temporal credit assignment problem is a central challenge in Reinforcement Learning (RL), concerned with attributing the appropriate influence to each actions in a trajectory for their ability to achieve a goal. However, when feedback…

Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding…

机器学习 · 计算机科学 2024-07-23 Yihang Yao , Zhepeng Cen , Wenhao Ding , Haohong Lin , Shiqi Liu , Tingnan Zhang , Wenhao Yu , Ding Zhao

Offline goal-conditioned reinforcement learning (GCRL) offers a practical learning paradigm in which goal-reaching policies are trained from abundant state-action trajectory datasets without additional environment interaction. However,…

机器学习 · 计算机科学 2025-11-05 Hongjoon Ahn , Heewoong Choi , Jisu Han , Taesup Moon

The ability to plan into the future while utilizing only raw high-dimensional observations, such as images, can provide autonomous agents with broad capabilities. Visual model-based reinforcement learning (RL) methods that plan future…

机器学习 · 计算机科学 2021-08-10 Oleh Rybkin , Chuning Zhu , Anusha Nagabandi , Kostas Daniilidis , Igor Mordatch , Sergey Levine