Imitation learning algorithms provide state-of-the-art results on many structured prediction tasks by learning near-optimal search policies. Such algorithms assume training-time access to an expert that can provide the optimal action at any queried state; unfortunately, the number of such queries is often prohibitive, frequently rendering these approaches impractical. To combat this query complexity, we consider an active learning setting in which the learning algorithm has additional access to a much cheaper noisy heuristic that provides noisy guidance. Our algorithm, LEAQI, learns a difference classifier that predicts when the expert is likely to disagree with the heuristic, and queries the expert only when necessary. We apply LEAQI to three sequence labeling tasks, demonstrating significantly fewer queries to the expert and comparable (or better) accuracies over a passive approach.
Robust learning from noisy demonstrations is a practical but highly challenging problem in imitation learning. In this paper, we first theoretically show that robust imitation learning can be achieved by optimizing a classification risk with a symmetric loss. Based on this theoretical finding, we then propose a new imitation learning method that optimizes the classification risk by effectively combining pseudo-labeling with co-training. Unlike existing methods, our method does not require additional labels or strict assumptions about noise distributions. Experimental results on continuous-cont…
Neurosymbolic Imitation Learning with Human Guidance: A Privileged Information Approach
Department of Computer Science, The University of Texas at Dallas, Richardson TX 75080, USA（德克萨斯大学达拉斯分校计算机科学系）；Computer Science Department and Centre for Cognitive Science, TU Darmstadt, Germany（德累斯顿技术大学计算机科学系和认知科学中心）
California Institute of Technology（加州理工学院）；Microsoft Research（微软研究院）；University of Maryland（马里兰大学）
We study how to effectively leverage expert feedback to learn sequential decision-making policies. We focus on problems with sparse rewards and long time horizons, which typically pose significant challenges in reinforcement learning. We propose an algorithmic framework, called hierarchical guidance, that leverages the hierarchical structure of the underlying problem to integrate different modes of expert interaction. Our framework can incorporate different combinations of imitation learning (IL) and reinforcement learning (RL) at different levels, leading to dramatic reductions in both expert…
Technion Israel Institute of Technology（以色列理工学院）；DeepMind（深度思维）；Google Research（谷歌研究院）
We propose a computationally efficient algorithm that combines compressed sensing with imitation learning to solve text-based games with combinatorial action spaces. Specifically, we introduce a new compressed sensing algorithm, named IK-OMP, which can be seen as an extension to the Orthogonal Matching Pursuit (OMP). We incorporate IK-OMP into a supervised imitation learning setting and show that the combined approach (Sparse Imitation Learning, Sparse-IL) solves the entire text-based game of Zork1 with an action space of approximately 10 million actions given both perfect and noisy demonstrat…
Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learning
Department of Physics, J.K. Institute of Science（J.K.科学研究院物理系）；World Scientific University（世界科学大学）；University of Intelligent Studies（智能研究大学）；Technical University of Crete（克里特技术大学）
Reinforcement learning, evolutionary algorithms and imitation learning are three principal methods to deal with continuous control tasks. Reinforcement learning is sample efficient, yet sensitive to hyper-parameters setting and needs efficient exploration; Evolutionary algorithms are stable, but with low sample efficiency; Imitation learning is both sample efficient and stable, however it requires the guidance of expert data. In this paper, we propose Recruitment-imitation Mechanism (RIM) for evolutionary reinforcement learning, a scalable framework that combines advantages of the three method…
Tsinghua University（清华大学）；Tencent AI Lab（腾讯人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
This paper studies Learning from Observations (LfO) for imitation learning with access to state-only demonstrations. In contrast to Learning from Demonstration (LfD) that involves both action and state supervision, LfO is more practical in leveraging previously inapplicable resources (e.g. videos), yet more challenging due to the incomplete expert guidance. In this paper, we investigate LfO and its difference with LfD in both theoretical and practical perspectives. We first prove that the gap between LfD and LfO actually lies in the disagreement of inverse dynamics models between the imitator …
University of Montreal（蒙特利尔大学）；Microsoft Research（微软研究院）；Google Research（谷歌研究院）；Aalto University（阿尔托大学）
We propose a novel regularizer for supervised learning called Conditioning on Noisy Targets (CNT). This approach consists in conditioning the model on a noisy version of the target(s) (e.g., actions in imitation learning or labels in classification) at a random noise level (from small to large noise). At inference time, since we do not know the target, we run the network with only noise in place of the noisy target. CNT provides hints through the noisy label (with less noise, we can more easily infer the true target). This give two main benefits: 1) the top-down feedback allows the model to fo…
Despite the numerous breakthroughs achieved with Reinforcement Learning (RL), solving environments with sparse rewards remains a challenging task that requires sophisticated exploration. Learning from Demonstrations (LfD) remedies this issue by guiding the agent's exploration towards states experienced by an expert. Naturally, the benefits of this approach hinge on the quality of demonstrations, which are rarely optimal in realistic scenarios. Modern LfD algorithms require meticulous tuning of hyperparameters that control the influence of demonstrations and, as we show in the paper, struggle w…
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Nanjing University（南京大学）
Behavioral cloning (BC) can recover a good policy from abundant expert data, but may fail when expert data is insufficient. This paper considers a situation where, besides the small amount of expert data, a supplementary dataset is available, which can be collected cheaply from sub-optimal policies. Imitation learning with a supplementary dataset is an emergent practical framework, but its theoretical foundation remains under-developed. To advance understanding, we first investigate a direct extension of BC, called NBCU, that learns from the union of all available data. Our analysis shows that…
GRAIL: Goal Recognition Alignment through Imitation Learning
Department of Computer Science, Bar Ilan University（巴伊兰大学计算机科学系）；Department of Computer Science, Aberdeen University（阿伯丁大学计算机科学系）；Department of Computer Science, Tufts University（塔夫茨大学计算机科学系）
Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization
School of Medicine, Stanford University（斯坦福大学医学院）；Data Science Institute, University of Chicago（芝加哥大学数据科学研究所）；Pritzker School of Molecular Engineering, University of Chicago（芝加哥大学普利兹克分子工程学院）；Department of Computer Science, University of Chicago（芝加哥大学计算机科学系）；Argonne National Laboratory（阿贡国家实验室）
University of Leeds（利兹大学）；Xi’an Jiaotong University（西安交通大学）
Crowd simulation is a central topic in several fields including graphics. To achieve high-fidelity simulations, data has been increasingly relied upon for analysis and simulation guidance. However, the information in real-world data is often noisy, mixed and unstructured, making it difficult for effective analysis, therefore has not been fully utilized. With the fast-growing volume of crowd data, such a bottleneck needs to be addressed. In this paper, we propose a new framework which comprehensively tackles this problem. It centers at an unsupervised method for analysis. The method takes as in…
Columbia University（哥伦比亚大学）；Didi Chuxing Inc.（滴滴出行有限公司）；National Maglev Transportation Engineering R&D Center, Tongji University（同济大学国家磁浮交通工程技术研究中心）；University of Michigan Transportation Research Institute, University of Michigan（密歇根大学密歇根大学交通研究所）；Ford School of Public Policy, University of Michigan（密歇根大学福特公共政策学院）
Vacant taxi drivers' passenger seeking process in a road network generates additional vehicle miles traveled, adding congestion and pollution into the road network and the environment. This paper aims to employ a Markov Decision Process (MDP) to model idle e-hailing drivers' optimal sequential decisions in passenger-seeking. Transportation network companies (TNC) or e-hailing (e.g., Didi, Uber) drivers exhibit different behaviors from traditional taxi drivers because e-hailing drivers do not need to actually search for passengers. Instead, they reposition themselves so that the matching platfo…
University of California Berkeley（加州大学伯克利分校）；University of Waterloo（滑铁卢大学）；University of Toronto（多伦多大学）；Columbia University（哥伦比亚大学）
A novel framework for solving the optimal execution and placement problems using reinforcement learning (RL) with imitation was proposed. The RL agents trained from the proposed framework consistently outperformed the industry benchmark time-weighted average price (TWAP) strategy in execution cost and showed great generalization across out-of-sample trading dates and tickers. The impressive performance was achieved from three aspects. First, our RL network architecture called Dual-window Denoise PPO enabled efficient learning in a noisy market environment. Second, a reward scheme with imitatio…
