Imitation Learning: Progress, Taxonomies and Challenges

Abstract

Imitation learning aims to extract knowledge from human experts' demonstrations or artificially created agents in order to replicate their behaviors. Its success has been demonstrated in areas such as video games, autonomous driving, robotic simulations and object manipulation. However, this replicating process could be problematic, such as the performance is highly dependent on the demonstration quality, and most trained agents are limited to perform well in task-specific environments. In this survey, we provide a systematic review on imitation learning. We first introduce the background knowledge from development history and preliminaries, followed by presenting different taxonomies within Imitation Learning and key milestones of the field. We then detail challenges in learning strategies and present research opportunities with learning policy from suboptimal demonstration, voice instructions and other associated optimization schemes.

References in corpus (26)

• Continuous control with deep reinforcement learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Trust Region Policy Optimization
• Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization
• Deep Q-learning from Demonstrations
• Third-Person Imitation Learning
• Multi-Agent Generative Adversarial Imitation Learning
• Reinforcement and Imitation Learning via Interactive No-Regret Learning
• Optimal Passenger-Seeking Policies on E-hailing Platforms Using Markov Decision Process and Imitation Learning
• Learning to Search Better Than Your Teacher
• Generative Adversarial Imitation from Observation
• Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction
• Learning Montezuma's Revenge from a Single Demonstration
• Imitating Latent Policies from Observation
• Generating Multi-Agent Trajectories using Programmatic Weak Supervision
• Deep Reinforcement Learning from Policy-Dependent Human Feedback
• Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations
• Provably Efficient Imitation Learning from Observation Alone
• On the Sample Complexity of Stability Constrained Imitation Learning
• Intrinsic Reward Driven Imitation Learning via Generative Model
• Imitation Learning for End to End Vehicle Longitudinal Control with Forward Camera
• Off-Policy Imitation Learning from Observations
• Non-Adversarial Imitation Learning and its Connections to Adversarial Methods
• An Imitation Learning Approach for Cache Replacement
• Robust Maximum Entropy Behavior Cloning
• Self-Imitation Learning by Planning