paper-with-me

홈 › Papers

Imitator Learning: Achieve Out-of-the-Box Imitation Ability in Variable Environments

2023-10-09 · Xiong-Hui Chen, Junyin Ye, Hang Zhao, Yi-Chen Li, Haoran Shi, Yu-Yan Xu, Zhihao Ye, Si-Hang Yang, Anqi Huang, Kai Xu, Zongzhang Zhang, Yang Yu

Imitation learning (IL) enables agents to mimic expert behaviors. Most previous IL techniques focus on precisely imitating one policy through mass demonstrations. However, in many applications, what humans require is the ability to perform various tasks directly through a few demonstrations of corresponding tasks, where the agent would meet many unexpected changes when deployed. In this scenario, the agent is expected to not only imitate the demonstration but also adapt to unforeseen environmental changes. This motivates us to propose a new topic called imitator learning (ItorL), which aims to derive an imitator module that can on-the-fly reconstruct the imitation policies based on very limited expert demonstrations for different unseen tasks, without any extra adjustment. In this work, we focus on imitator learning based on only one expert demonstration. To solve ItorL, we propose Demo-Attention Actor-Critic (DAAC), which integrates IL into a reinforcement-learning paradigm that can regularize policies' behaviors in unexpected situations. Besides, for autonomous imitation policy building, we design a demonstration-based attention architecture for imitator policy that can effectively output imitated actions by adaptively tracing the suitable states in demonstrations. We develop a new navigation benchmark and a robot environment for \topic~and show that DAAC~outperforms previous imitation methods \textit{with large margins} both on seen and unseen tasks.

📄 PDF Abstract BibTeX arXiv:2310.05712

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Fully General Online Imitation Learning

2021-02-17 · Michael K. Cohen, Marcus Hutter, Neel Nanda

In imitation learning, imitators and demonstrators are policies for picking actions given past interactions with the environment. If we run an imitator, we probably want events to unfold similarly to the way they would h…

Imitation Learning

Out-of-Dynamics Imitation Learning from Multimodal Demonstrations

2022-11-13 · Yiwen Qiu, Jialong Wu, Zhangjie Cao, Mingsheng Long

Existing imitation learning works mainly assume that the demonstrator who collects demonstrations shares the same dynamics as the imitator. However, the assumption limits the usage of imitation learning, especially when …

Imitation LearningMuJoCo

Sequential Causal Imitation Learning with Unobserved Confounders

2022-08-12 · NeurIPS 2021 12 · Daniel Kumor, Junzhe Zhang, Elias Bareinboim

"Monkey see monkey do" is an age-old adage, referring to na\"ive imitation without a deep understanding of a system's underlying mechanics. Indeed, if a demonstrator has access to information unavailable to the imitator …

Decision MakingImitation Learning

Smart Imitator: Learning from Imperfect Clinical Decisions

2025-01-10 · Journal of American Medical Informatics Association 2025 1 · Dilruk Perera, SiQi Liu, Kay Choong See, Mengling Feng

Objectives: This study introduces Smart Imitator (SI), a 2-phase reinforcement learning (RL) solution enhancing personalized treatment policies in healthcare, addressing challenges from imperfect clinician data and comp…

Imitation LearningReinforcement Learning (RL)

Invariant Causal Imitation Learning for Generalizable Policies

2023-11-02 · NeurIPS 2021 12 · Ioana Bica, Daniel Jarrett, Mihaela van der Schaar

Consider learning an imitation policy on the basis of demonstrated behavior from multiple environments, with an eye towards deployment in an unseen environment. Since the observable features from each setting may be diff…

Imitation Learning