English
Related papers

Related papers: Self-Imitation Learning by Planning

200 papers

Following the impressive capabilities of in-context learning with large transformers, In-Context Imitation Learning (ICIL) is a promising opportunity for robotics. We introduce Instant Policy, which learns new tasks instantly (without…

Robotics · Computer Science 2025-04-28 Vitalis Vosylius , Edward Johns

Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot…

Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for…

Machine Learning · Computer Science 2023-10-24 Siyuan Li , Xun Wang , Rongchang Zuo , Kewu Sun , Lingfei Cui , Jishiyu Ding , Peng Liu , Zhe Ma

Classical policy search algorithms for robotics typically require performing extensive explorations, which are time-consuming and expensive to implement with real physical platforms. To facilitate the efficient learning of robot…

Robotics · Computer Science 2023-04-25 Shengzeng Huo , Anqing Duan , Lijun Han , Luyin Hu , Hesheng Wang , David Navarro-Alarcon

Automatic laparoscope motion control is fundamentally important for surgeons to efficiently perform operations. However, its traditional control methods based on tool tracking without considering information hidden in surgical scenes are…

Robotics · Computer Science 2022-04-08 Bin Li , Ruofeng Wei , Jiaqi Xu , Bo Lu , Chi-Hang Yee , Chi-Fai Ng , Pheng-Ann Heng , Qi Dou , Yun-Hui Liu

Imitation learning (IL) with human demonstrations is a promising method for robotic manipulation tasks. While minimal demonstrations enable robotic action execution, achieving high success rates and generalization requires high cost, e.g.,…

Today's robots attempt to learn new tasks by imitating human examples. These robots watch the human complete the task, and then try to match the actions taken by the human expert. However, this standard approach to visual imitation learning…

We study Imitation Learning (IL) from Observations alone (ILFO) in large-scale MDPs. While most IL algorithms rely on an expert to directly provide actions to the learner, in this setting the expert only supplies sequences of observations.…

Machine Learning · Computer Science 2019-06-12 Wen Sun , Anirudh Vemula , Byron Boots , J. Andrew Bagnell

Reinforcement learning methods as a promising technique have achieved superior results in the motion planning of free-floating space robots. However, due to the increase in planning dimension and the intensification of system dynamics…

Robotics · Computer Science 2022-09-07 Yuxue Cao , Shengjie Wang , Xiang Zheng , Wenke Ma , Xinru Xie , Lei Liu

Reinforcement learning (RL) with dense rewards and imitation learning (IL) with human-generated trajectories are the most widely used approaches for training modern embodied agents. RL requires extensive reward shaping and auxiliary losses…

Planning methods can solve temporally extended sequential decision making problems by composing simple behaviors. However, planning requires suitable abstractions for the states and transitions, which typically need to be designed by hand.…

Machine Learning · Computer Science 2019-11-20 Soroush Nasiriany , Vitchyr H. Pong , Steven Lin , Sergey Levine

Many challenging reinforcement learning (RL) problems require designing a distribution of tasks that can be applied to train effective policies. This distribution of tasks can be specified by the curriculum. A curriculum is meant to improve…

Machine Learning · Computer Science 2023-01-03 Maria Nesterova , Alexey Skrynnik , Aleksandr Panov

Today's autonomous agents, largely driven by foundation models (FMs), can understand natural language instructions and solve long-horizon tasks with human-like reasoning. However, current human-robot interaction largely follows a one-way…

Robotics · Computer Science 2026-03-17 Linus Nwankwo , Bjoern Ellensohn , Christian Rauch , Elmar Rueckert

Meta-reinforcement learning (Meta-RL) facilitates rapid adaptation to unseen tasks but faces challenges in long-horizon environments. Skill-based approaches tackle this by decomposing state-action sequences into reusable skills and…

Machine Learning · Computer Science 2026-05-21 Sanghyeon Lee , Sangjun Bae , Yisak Park , Seungyul Han

Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function. However, it presents unique challenges with large amounts of environment…

Machine Learning · Computer Science 2020-03-10 Neda Navidi

Imitation learning methods seek to learn from an expert either through behavioral cloning (BC) of the policy or inverse reinforcement learning (IRL) of the reward. Such methods enable agents to learn complex tasks from humans that are…

Machine Learning · Computer Science 2023-12-07 Joe Watson , Sandy H. Huang , Nicolas Heess

Implementing intelligent control of robots is a difficult task, especially when dealing with complex black-box systems, because of the lack of visibility and understanding of how these robots work internally. This paper proposes an…

Artificial Intelligence · Computer Science 2023-11-14 Xubo Yang , Jian Gao , Ting Wang , Yaozhen He

Deep imitation learning enables robots to learn from expert demonstrations to perform tasks such as lane following or obstacle avoidance. However, in the traditional imitation learning framework, one model only learns one task, and thus it…

Computer Vision and Pattern Recognition · Computer Science 2018-08-19 Junhong Xu , Qiwei Liu , Hanqing Guo , Aaron Kageza , Saeed AlQarni , Shaoen Wu

Imitation learning (IL) is a frequently used approach for data-efficient policy learning. Many IL methods, such as Dataset Aggregation (DAgger), combat challenges like distributional shift by interacting with oracular experts.…

Robotics · Computer Science 2021-06-08 Mandy Xie , Anqi Li , Karl Van Wyk , Frank Dellaert , Byron Boots , Nathan Ratliff

Learning-based methods for dexterous manipulation have made notable progress in recent years. However, learned policies often still lack reliability and exhibit limited robustness to important factors of variation. One failure pattern that…

‹ Prev 1 3 4 5 6 7 10 Next ›