Abstracting Reusable Cases from Reinforcement Learning
نویسندگان
چکیده
ing Reusable Cases from Reinforcement Learning Andreas von Hessling and Ashok K. Goel College of Computing Georgia Institute of Technology Atlanta, GA 30318 {avh, goel}@cc.gatech.edu Abstract. Reinforcement Learning is a popular technique for gameplaying because it can learn an optimal policy for sequential decision problems in which the outcome (or reward) is delayed. However, Reinforcement Learning does not readily enable transfer of acquired knowledge to other instances. Case-Based Reasoning, in contrast, addresses exactly the issue of transferring solutions to slightly different instances of a problem. We describe a technique for abstracting reusable cases from Reinforcement Learning. We also report on preliminary experiments with case abstraction in a microworld.
منابع مشابه
Situationally Aware Options
Hierarchical abstractions, also known as options – a type of temporally extended action (Sutton et al., 1999) that enables a reinforcement learning agent to plan at a higher level, abstracting away from the lower-level details. In this work, we learn reusable options whose parameters can vary, encouraging different behaviors, based on the current situation. In principle, these behaviors can inc...
متن کاملReusable Reinforcement Learning for Modular Self Motivated Agents
Presented topic is from the research fields called Artificial Life and Artificial Intelligence (AI). In this paper, there is presented novel approach to designing agent architectures with its requirements. The approach is inspired by inherited modularity of biological brains and agent architectures are represented here as set of given reusable modules connected into a particular topology. This ...
متن کاملLearning and Transfer: A General Role for Analogical Encoding
Teaching by examples and cases is widely used to promote learning, but it varies widely in its effectiveness. The authors test an adaptation to case-based learning that facilitates abstracting problemsolving schemas from examples and using them to solve further problems: analogical encoding, or learning by drawing a comparison across examples. In 3 studies, the authors examined schema abstracti...
متن کاملA Deep Hierarchical Approach to Lifelong Learning in Minecraft
The ability to reuse or transfer knowledge from one task to another in lifelong learning problems, such as Minecraft, is one of the major challenges faced in AI. Reusing knowledge across tasks is crucial to solving tasks efficiently with lower sample complexity. We provide a Reinforcement Learning agent with the ability to transfer knowledge by learning reusable skills, a type of temporally ext...
متن کاملImitation Learning in The Game of Go with Joseki Options
Scaling reinforcement learning methods to large, challenging decision making tasks can potentially benefit from integrating domain specific knowledge in a principled manner. This synthesis focuses on applying two forms of domain knowledge about the game of Go to improve learning performance on what continues to be an extremely challenging task. First, learning is bootstrapped by using reinforce...
متن کامل