Constrained Reinforcement Learning for Robotics via Scenario-Based Programming

06/20/2022
by   Davide Corsi, et al.
0

Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications. A natural consequence is the adoption of this paradigm for safety-critical tasks, where human safety and expensive hardware can be involved. In this context, it is crucial to optimize the performance of DRL-based agents while providing guarantees about their behavior. This paper presents a novel technique for incorporating domain-expert knowledge into a constrained DRL training loop. Our technique exploits the scenario-based programming paradigm, which is designed to allow specifying such knowledge in a simple and intuitive way. We validated our method on the popular robotic mapless navigation problem, in simulation, and on the actual platform. Our experiments demonstrate that using our approach to leverage expert knowledge dramatically improves the safety and the performance of the agent.

READ FULL TEXT
research
08/03/2023

SMARLA: A Safety Monitoring Approach for Deep Reinforcement Learning Agents

Deep reinforcement learning algorithms (DRL) are increasingly being used...
research
03/29/2023

Physical Deep Reinforcement Learning Towards Safety Guarantee

Deep reinforcement learning (DRL) has achieved tremendous success in man...
research
01/20/2021

Shielding Atari Games with Bounded Prescience

Deep reinforcement learning (DRL) is applied in safety-critical domains ...
research
02/13/2023

Online Safety Property Collection and Refinement for Safe Deep Reinforcement Learning in Mapless Navigation

Safety is essential for deploying Deep Reinforcement Learning (DRL) algo...
research
09/06/2021

Safe Reinforcement Learning using Formal Verification for Tissue Retraction in Autonomous Robotic-Assisted Surgery

Deep Reinforcement Learning (DRL) is a viable solution for automating re...
research
02/08/2021

Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks

Deep Reinforcement Learning (DRL) is emerging as a promising approach to...
research
05/15/2019

Deep Reinforcement Learning for Scheduling in Cellular Networks

Integrating artificial intelligence (AI) into wireless networks has draw...

Please sign up or login with your details

Forgot password? Click here to reset