An Introduction to Deep Reinforcement and Imitation Learning
By: Pedro Santana
Potential Business Impact:
Teaches robots to learn by watching and trying.
Embodied agents, such as robots and virtual characters, must continuously select actions to execute tasks effectively, solving complex sequential decision-making problems. Given the difficulty of designing such controllers manually, learning-based approaches have emerged as promising alternatives, most notably Deep Reinforcement Learning (DRL) and Deep Imitation Learning (DIL). DRL leverages reward signals to optimize behavior, while DIL uses expert demonstrations to guide learning. This document introduces DRL and DIL in the context of embodied agents, adopting a concise, depth-first approach to the literature. It is self-contained, presenting all necessary mathematical and machine learning concepts as they are needed. It is not intended as a survey of the field; rather, it focuses on a small set of foundational algorithms and techniques, prioritizing in-depth understanding over broad coverage. The material ranges from Markov Decision Processes to REINFORCE and Proximal Policy Optimization (PPO) for DRL, and from Behavioral Cloning to Dataset Aggregation (DAgger) and Generative Adversarial Imitation Learning (GAIL) for DIL.
Similar Papers
Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning
Robotics
Teaches robots to learn tasks faster and better.
Going Beyond Expert Performance via Deep Implicit Imitation Reinforcement Learning
Machine Learning (CS)
Teaches robots to learn from watching, not just doing.
A Practical Introduction to Deep Reinforcement Learning
Machine Learning (CS)
Teaches computers to learn and make smart choices.