Teaching Reinforcement Learning using a Physical Robot
نویسندگان
چکیده
This paper presents a little crawling robot as a didactic instrument for teaching reinforcement learning. The robot learns a forwardwalking policy from scratch in less than 20 seconds of reinforced sensorimotor interactions. The state space consists of two discretized dimensions, where the behavior is visualizable and comprehensible. In laboratory tutorials, students conduct experiments with a Toolbox written in Java, enabling to vary significant parameters such as the exploration rate or the discounting factor. Our experience as well students feedback in using the crawler reflects: (1) a more interesting lecture, (2) an increase in students’ motivation, and (3) an efficient and fast learning for students.
منابع مشابه
Dynamic Obstacle Avoidance by Distributed Algorithm based on Reinforcement Learning (RESEARCH NOTE)
In this paper we focus on the application of reinforcement learning to obstacle avoidance in dynamic Environments in wireless sensor networks. A distributed algorithm based on reinforcement learning is developed for sensor networks to guide mobile robot through the dynamic obstacles. The sensor network models the danger of the area under coverage as obstacles, and has the property of adoption o...
متن کاملLego Mindstorms Robots as a Platform for Teaching Reinforcement Learning
This paper examines the suitability of Lego Mindstorms robotic kits as a platform for teaching the concepts of reinforcement learning. The reinforcement learning algorithm Sarsa was implemented on board an autonomous Mindstorms robot, and applied to two learning tasks. The reasons behind the differing results obtained on these two tasks are discussed, and several issues related to the suitab...
متن کاملTeaching Robots to Coordinate their Behaviours
Behaviour co-ordination is one of the major problems in behaviour-based robotics. This paper presents a teaching method for mobile robots to learn the behaviour coordination. In this method, the sensory information is abstracted into a limited number of feature states that correspond to physical events in the interactive process between a robot and its environment. The continuous motor actions ...
متن کاملIntegrating Human Instructions and Reinforcement Learners : An SRL Approach
As robots and other intelligent systems move out from tailored environments and enter the real world they would have to adapt quickly and learn from their surroundings. Like humans, they would have to learn from various sources experience, peers, teachers, trialand-error etc. In earlier work, we proposed a framework that facilitates a teacher-student like relationship between humans and robots,...
متن کاملToward Probabilistic Safety Bounds for Robot Learning from Demonstration
Learning from demonstration is a popular method for teaching robots new skills. However, little work has looked at how to measure safety in the context of learning from demonstrations. We discuss three different types of safety problems that are important for robot learning from human demonstrations: (1) using demonstrations to evaluate the safety of a robot’s current policy, (2) using demonstr...
متن کامل