Global overview of Imitation Learning

Abstract

Imitation Learning is a sequential task where the learner tries to mimic an expert's action in order to achieve the best performance. Several algorithms have been proposed recently for this task. In this project, we aim at proposing a wide review of these algorithms, presenting their main features and comparing them on their performance and their regret bounds.

arXiv comment9 pages, 5 figures, 5 appendix pages

References in corpus (2)

• Reinforcement and Imitation Learning via Interactive No-Regret Learning
• Active Imitation Learning via Reduction to I.I.D. Active Learning

Cited by in corpus (14)

• Neural Network Decoders for Large-Distance 2D Toric Codes
• Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines
• Strictly Batch Imitation Learning by Energy-based Distribution Matching
• Attacking Vision-based Perception in End-to-End Autonomous Driving Models
• Navigation by Imitation in a Pedestrian-Rich Environment
• Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning
• Human AI interaction loop training: New approach for interactive reinforcement learning
• Transferable Active Grasping and Real Embodied Dataset
• Transfer Learning for Prosthetics Using Imitation Learning
• Human and Multi-Agent collaboration in a human-MARL teaming framework
• A Novel Deep Neural Network Architecture for Mars Visual Navigation
• Inspiration Learning through Preferences
• Meta Adaptation using Importance Weighted Demonstrations
• Augmented Q Imitation Learning (AQIL)