Adversarial imitation learning has become a widely used imitation learning framework. The discriminator is often trained by taking expert demonstrations and policy trajectories as examples respectively from two categories (positive vs. negative) and the policy is then expected to produce trajectories that are indistinguishable from the expert demonstrations. But in the real world, the collected expert demonstrations are more likely to be imperfect, where only an unknown fraction of the demonstrations are optimal. Instead of treating imperfect expert demonstrations as absolutely positive or negative, we investigate unlabeled imperfect expert demonstrations as they are. A positive-unlabeled adversarial imitation learning algorithm is developed to dynamically sample expert demonstrations that can well match the trajectories from the constantly optimized agent policy. The trajectories of an initial agent policy could be closer to those non-optimal expert demonstrations, but within the framework of adversarial imitation learning, agent policy will be optimized to cheat the discriminator and produce trajectories that are similar to those optimal expert demonstrations. Theoretical analysis shows that our method learns from the imperfect demonstrations via a self-paced way. Experimental results on MuJoCo and RoboSuite platforms demonstrate the effectiveness of our method from different aspects.
National Taiwan University（台湾大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；The University of Tokyo（东京大学）
Imitation learning (IL) aims to learn an optimal policy from demonstrations. However, such demonstrations are often imperfect since collecting optimal ones is costly. To effectively learn from imperfect demonstrations, we propose a novel approach that utilizes confidence scores, which describe the quality of demonstrations. More specifically, we propose two confidence-based IL methods, namely two-step importance weighting IL (2IWIL) and generative adversarial IL with imperfect demonstration and confidence (IC-GAIL). We show that confidence scores given only to a small portion of sub-optimal de…
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zurich（苏黎世联邦理工学院）
Learning diverse skills is one of the main challenges in robotics. To this end, imitation learning approaches have achieved impressive results. These methods require explicitly labeled datasets or assume consistent skill execution to enable learning and active control of individual behaviors, which limits their applicability. In this work, we propose a cooperative adversarial method for obtaining single versatile policies with controllable skill sets from unlabeled datasets containing diverse state transition patterns by maximizing their discriminability. Moreover, we show that by utilizing un…
Imitation learning enables robots to learn from demonstrations. Previous imitation learning algorithms usually assume access to optimal expert demonstrations. However, in many real-world applications, this assumption is limiting. Most collected demonstrations are not optimal or are produced by an agent with slightly different dynamics. We therefore address the problem of imitation learning when the demonstrations can be sub-optimal or be drawn from agents with varying dynamics. We develop a metric composed of a feasibility score and an optimality score to measure how useful a demonstration is …
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）
Behavioral cloning (BC) bears a high potential for safe and direct transfer of human skills to robots. However, demonstrations performed by human operators often contain noise or imperfect behaviors that can affect the efficiency of the imitator if left unchecked. In order to allow the imitators to effectively learn from imperfect demonstrations, we propose to employ the robust t-momentum optimization algorithm. This algorithm builds on the Student's t-distribution in order to deal with heavy-tailed data and reduce the effect of outlying observations. We extend the t-momentum algorithm to allo…
Learning What to Do and What Not To Do: Offline Imitation from Expert and Undesirable Demonstrations
Singapore Management University（新加坡管理大学）；Institute of High Performance Computing（高性能计算研究所）；Agency for Science, Technology and Research, Singapore（新加坡科技研究局）
Deep reinforcement learning (DRL) provides a new way to generate robot control policy. However, the process of training control policy requires lengthy exploration, resulting in a low sample efficiency of reinforcement learning (RL) in real-world tasks. Both imitation learning (IL) and learning from demonstrations (LfD) improve the training process by using expert demonstrations, but imperfect expert demonstrations can mislead policy improvement. Offline to Online reinforcement learning requires a lot of offline data to initialize the policy, and distribution shift can easily lead to performan…
Offline imitation learning (IL) promises the ability to learn performant policies from pre-collected demonstrations without interactions with the environment. However, imitating behaviors fully offline typically requires numerous expert data. To tackle this issue, we study the setting where we have limited expert data and supplementary suboptimal data. In this case, a well-known issue is the distribution shift between the learned policy and the behavior policy that collects the offline data. Prior works mitigate this issue by regularizing the KL divergence between the stationary state-action d…
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations. However, BC does not effectively leverage what we will refer to as unlabeled experience: data of mixed and unknown quality without reward annotations. This unlabeled data can be generated by a variety of sources such as human teleoperation, scripted policies and other agents on the same robot. Towards data-driven offline robot learning that can use this unlabeled experience, we introduce Offline Reinforced Imitation Learn…
Control policies from imitation learning can often fail to generalize to novel environments due to imperfect demonstrations or the inability of imitation learning algorithms to accurately infer the expert's policies. In this paper, we present rigorous generalization guarantees for imitation learning by leveraging the Probably Approximately Correct (PAC)-Bayes framework to provide upper bounds on the expected cost of policies in novel environments. We propose a two-stage training method where a latent policy distribution is first embedded with multi-modal expert behavior using a conditional var…
The performance of imitation learning is typically upper-bounded by the performance of the demonstrator. While recent empirical results demonstrate that ranked demonstrations allow for better-than-demonstrator performance, preferences over demonstrations may be difficult to obtain, and little is known theoretically about when such methods can be expected to successfully extrapolate beyond the performance of the demonstrator. To address these issues, we first contribute a sufficient condition for better-than-demonstrator imitation learning and provide theoretical results showing why preferences…
University College London（伦敦大学学院）；Cohere（Cohere公司）
With the advent of large datasets, offline reinforcement learning (RL) is a promising framework for learning good decision-making policies without the need to interact with the real environment. However, offline RL requires the dataset to be reward-annotated, which presents practical challenges when reward engineering is difficult or when obtaining reward annotations is labor-intensive. In this paper, we introduce Optimal Transport Reward labeling (OTR), an algorithm that assigns rewards to offline trajectories, with a few high-quality demonstrations. OTR's key idea is to use optimal transport…
The goal of imitation learning is for an apprentice to learn how to behave in a stochastic environment by observing a mentor demonstrating the correct behavior. Accurate prior knowledge about the correct behavior can reduce the need for demonstrations from the mentor. We present a novel approach to encoding prior knowledge about the correct behavior, where we assume that this prior knowledge takes the form of a Markov Decision Process (MDP) that is used by the apprentice as a rough and imperfect model of the mentor's behavior. Specifically, taking a Bayesian approach, we treat the value of a p…
Learning reward functions from data is a promising path towards achieving scalable Reinforcement Learning (RL) for robotics. However, a major challenge in training agents from learned reward models is that the agent can learn to exploit errors in the reward model to achieve high reward behaviors that do not correspond to the intended task. These reward delusions can lead to unintended and even dangerous behaviors. On the other hand, adversarial imitation learning frameworks tend to suffer the opposite problem, where the discriminator learns to trivially distinguish agent and expert behavior, r…
Imitation Learning from Observation with Automatic Discount Scheduling
Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Shanghai Qi Zhi Institute（上海期智研究院）；UC Berkeley（加州大学伯克利分校）；Washington University in St. Louis（圣路易斯华盛顿大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Existing learning from demonstration algorithms usually assume access to expert demonstrations. However, this assumption is limiting in many real-world applications since the collected demonstrations may be suboptimal or even consist of failure cases. We therefore study the problem of learning from imperfect demonstrations by learning a confidence predictor. Specifically, we rely on demonstrations along with their confidence values from a different correspondent environment (source environment) to learn a confidence predictor for the environment we aim to learn a policy in (target environment …
Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression
Westlake University（西湖大学）；Tsinghua University（清华大学）；University of Oxford（牛津大学）；Southwest University of Science and Technology（西南科技大学）；New Jersey Institute of Technology（新泽西理工学院）
Improving Behavioural Cloning with Positive Unlabeled Learning
University College Dublin（都柏林大学）；University College London（伦敦大学学院）；Dublin City University（都柏林城市大学）；Insight SFI Research Centre for Data Analytics（Insight SFI 数据分析研究中心）；MPI for Intelligent Systems（马克斯·普朗克智能系统研究所）
University of Toronto Robotics Institute（多伦多大学机器人研究所）；Vector Institute（向量研究所）；Montreal Institute of Learning Algorithms (MILA)（蒙特利尔学习算法研究所）；McGill University（麦吉尔大学）
The potential benefits of model-free reinforcement learning to real robotics systems are limited by its uninformed exploration that leads to slow convergence, lack of data-efficiency, and unnecessary interactions with the environment. To address these drawbacks we propose a method that combines reinforcement and imitation learning by shaping the reward function with a state-and-action-dependent potential that is trained from demonstration data, using a generative model. We show that this accelerates policy learning by specifying high-value areas of the state and action space that are worth exp…
University of California, Berkeley（加州大学伯克利分校）；Google Research（谷歌研究院）
Learning from demonstrations has made great progress over the past few years. However, it is generally data hungry and task specific. In other words, it requires a large amount of data to train a decent model on a particular task, and the model often fails to generalize to new tasks that have a different distribution. In practice, demonstrations from new tasks will be continuously observed and the data might be unlabeled or only partially labeled. Therefore, it is desirable for the trained model to adapt to new tasks that have limited data samples available. In this work, we build an adaptable…
