20% off all books with the code: BOOKS
  • check 10+ million books
  • check New arrivals every day
  • check Trusted by 1M+ customers
  • check Great prices & discounts
  • check Shipping across Europe

Explainable and Interpretable Reinforcement Learning for Robotics - Dinesh Manocha,Elham Tabassi,Aaron M. Roth,Ram D. Sriram

English
2024-03-20
€72.58 €90.73

-20% with code BOOKS

In stock at our supplier

Shipping in 17-23 days

30-day return policy

This book surveys the state of the art in explainable and interpretable reinforcement learning (RL) as relevant for robotics. While RL in general has grown in popularity and been applied to increasingly complex problems, several challenges have impeded the real-world adoption of RL algorithms for robotics and related areas. These include difficulties in preventing safety constraints from being violated and ... Full description

You May Also Like

Description

This book surveys the state of the art in explainable and interpretable reinforcement learning (RL) as relevant for robotics. While RL in general has grown in popularity and been applied to increasingly complex problems, several challenges have impeded the real-world adoption of RL algorithms for robotics and related areas. These include difficulties in preventing safety constraints from being violated and the issues faced by systems operators who desire explainable policies and actions. Robotics applications present a unique set of considerations and result in a number of opportunities related to their physical, real-world sensory input and interactions. The authors consider classification techniques used in past surveys and papers and attempt to unify terminology across the field. The book provides an in-depth exploration of 12 attributes that can be used to classify explainable/interpretable techniques. These include whether the RL method is model-agnostic or model-specific, self-explainable or post-hoc, as well as additional analysis of the attributes of scope, when-produced, format, knowledge limits, explanation accuracy, audience, predictability, legibility, readability, and reactivity. The book is organized around a discussion of these methods broken down into 42 categories and subcategories, where each category can be classified according to some of the attributes. The authors close by identifying gaps in the current research and highlighting areas for future investigation.

More Information

Write Your Own Review
You're reviewing: Explainable and Interpretable Reinforcement Learning for Robotics
Your Rating:

Goodreads Reviews

€72.58 €90.73