Imitation Learning

Abstract

Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years; however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations, without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction, and computer games, to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this article, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications, and highlight current and future research directions.

Cognitive Robotics: Making Robots Sense, Understand, and Interact

“…Employing human demon strations, a robot is trained to perform a task by learning a mapping between observations and actions. 8 Demonstra tions in connections with virtual reality and motion capture permit the efficient and scalable recording of demonstration data. Having an experienced human operator provide good examples to learn from speeds up the process of learning for a performant model.…”

Review of Deep Reinforcement Learning-Based Object Grasping: Techniques, Open Challenges, and Recommendations

“…Several studies have demonstrated the problem of robots in performing a task in the presence of stationary [181]- [183] or moving obstacles, which are regarded as a special consideration during demonstrations [184]. On the contrary, applying motion planning and task programming is considered a solution for avoiding the complexity of manual programming, and it can be provided by the LfD approach [185].…”

Emotion AI-Driven Sentiment Analysis: A Survey, Future Research Directions, and Open Issues

“…It discussed fine-grained sentiment analysis and algorithm classification. [24] To depict the n-gram, unigram, and focuses on interpreting the sentiment in every single sentence.…”