This paper presents the selective use of eye-gaze information in learning human actions in Atari games. Vast evidence suggests that our eye movement convey a wealth of information about the direction of our attention and mental states and encode the information necessary to complete a task. Based on this evidence, we hypothesize that selective use of eye-gaze, as a clue for attention direction, will enhance the learning from demonstration. For this purpose, we propose a selective eye-gaze augmentation (SEA) network that learns when to use the eye-gaze information. The proposed network architecture consists of three sub-networks: gaze prediction, gating, and action prediction network. Using the prior 4 game frames, a gaze map is predicted by the gaze prediction network which is used for augmenting the input frame. The gating network will determine whether the predicted gaze map should be used in learning and is fed to the final network to predict the action at the current frame. To validate this approach, we use publicly available Atari Human Eye-Tracking And Demonstration (Atari-HEAD) dataset consists of 20 Atari games with 28 million human demonstrations and 328 million eye-gazes (over game frames) collected from four subjects. We demonstrate the efficacy of selective eye-gaze augmentation in comparison with state of the art Attention Guided Imitation Learning (AGIL), Behavior Cloning (BC). The results indicate that the selective augmentation approach (the SEA network) performs significantly better than the AGIL and BC. Moreover, to demonstrate the significance of selective use of gaze through the gating network, we compare our approach with the random selection of the gaze. Even in this case, the SEA network performs significantly better validating the advantage of selectively using the gaze in demonstration learning.
Estimating Central, Peripheral, and Temporal Visual Contributions to Human Decision Making in Atari Games
Department of Advanced Interdisciplinary Studies, The University of Tokyo（东京大学先进跨学科研究系）；Research Center for Advanced Science and Technology, The University of Tokyo（东京大学先进科学与技术研究中心）
The Hong Kong University of Science and Technology（香港科技大学）
Vision-based autonomous driving through imitation learning mimics the behaviors of human drivers by training on pairs of data of raw driver-view images and actions. However, there are other cues, e.g. gaze behavior, available from human drivers that have yet to be exploited. Previous research has shown that novice human learners can benefit from observing experts' gaze patterns. We show here that deep neural networks can also benefit from this. We demonstrate different approaches to integrating gaze information into imitation networks. Our results show that the integration of gaze information …
University of Texas at Austin（得克萨斯大学奥斯汀分校）；Carnegie Mellon University（卡内基梅隆大学）
Large-scale public datasets have been shown to benefit research in multiple areas of modern artificial intelligence. For decision-making research that requires human data, high-quality datasets serve as important benchmarks to facilitate the development of new methods by providing a common reproducible standard. Many human decision-making tasks require visual attention to obtain high levels of performance. Therefore, measuring eye movements can provide a rich source of information about the strategies that humans use to solve decision-making tasks. Here, we provide a large-scale, high-quality …
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Tufts University（塔夫茨大学）
Human gaze is known to be an intention-revealing signal in human demonstrations of tasks. In this work, we use gaze cues from human demonstrators to enhance the performance of agents trained via three popular imitation learning methods -- behavioral cloning (BC), behavioral cloning from observation (BCO), and Trajectory-ranked Reward EXtrapolation (T-REX). Based on similarities between the attention of reinforcement learning agents and human gaze, we propose a novel approach for utilizing gaze data in a computationally efficient manner, as part of an auxiliary loss function, which guides a net…
University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google Inc.（谷歌公司）；Peking University（北京大学）
When intelligent agents learn visuomotor behaviors from human demonstrations, they may benefit from knowing where the human is allocating visual attention, which can be inferred from their gaze. A wealth of information regarding intelligent decision making is conveyed by human gaze allocation; hence, exploiting such information has the potential to improve the agents' performance. With this motivation, we propose the AGIL (Attention Guided Imitation Learning) framework. We collect high-quality human action and gaze data while playing Atari games in a carefully controlled experimental setting. …
To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. We train a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games. Our approach beats the imitation learning baseline in 7 games and achieves strictly superhuman performance on 2 games…
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Applied Research Laboratories, The University of Texas at Austin（德克萨斯大学奥斯汀分校应用研究实验室）
Bayesian reward learning from demonstrations enables rigorous safety and uncertainty analysis when performing imitation learning. However, Bayesian reward learning methods are typically computationally intractable for complex control problems. We propose Bayesian Reward Extrapolation (Bayesian REX), a highly efficient Bayesian reward learning algorithm that scales to high-dimensional imitation learning problems by pre-training a low-dimensional feature encoding via self-supervised tasks and then leveraging preferences over demonstrations to perform fast Bayesian inference. Bayesian REX can lea…
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…
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）
Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration
Department of Computer Science, University of California, Los Angeles（加州大学洛杉矶分校计算机科学系）；IHPC, Agency for Science, Technology and Research, Singapore（新加坡科技研究局信息与通信技术研究所）；CFAR, Agency for Science, Technology and Research, Singapore（新加坡科技研究局癌症研究基金会）
Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）；University of California, Berkeley（加州大学伯克利分校）
Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer from distribution shift: because the agent greedily imitates demonstrated actions, it can drift away from demonstrated states due to error accumulation. Recent methods based on reinforcement learning (RL), such as inverse RL and generative adversarial imitation learning (GAIL), overcome this issue by training an RL agent to match the demonstrations over a lo…
