Transcription of Benchmarking Safe Exploration in Deep Reinforcement Learning
{{id}} {{{paragraph}}}
Example: marketing
Benchmarking Safe Exploration in Deep Reinforcement Learning
Benchmarking Safe Exploration in Deep Reinforcement Learning Alex Ray Joshua Achiam Dario Amodei OpenAI OpenAI OpenAI. Abstract Reinforcement Learning (RL) agents need to explore their environments in order to learn optimal policies by trial and error. In many environments, safety is a critical concern and certain errors are unacceptable: for example, robotics systems that interact with humans should never cause injury to the humans while exploring. While it is currently typical to train RL agents mostly or entirely in simulation, where safety concerns are minimal, we anticipate that challenges in simulating the complexities of the real world (such as human-AI interactions) will cause a shift towards training RL agents directly in the real world, where safety concerns are paramount. Consequently we take the position that safe Exploration should be viewed as a critical focus area for RL research, and in this work we make three contributions to advance the study of safe Exploration .
covering a wide range of work, and offer valuable historical perspectives not covered here due to our choice to focus on modern RL with deep neural network function approximators. Safety Definitions and Algorithms: A foundational problem in safe exploration work is the question of what safety means in the first place.
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: