Reducing state space exploration in reinforcement learning problems by rapid identification of initial solutions and progressive improvement of them
نویسنده
چکیده
Most existing reinforcement learning methods require exhaustive state space exploration before converging towards a problem solution. Various generalization techniques have been used to reduce the need for exhaustive exploration, but for problems like maze route finding these techniques are not easily applicable. This paper presents an approach that makes it possible to reduce the need for state space exploration by rapidly identifying a "usable" solution. Concepts of shortand long term working memory then make it possible to continue exploring and find better or optimal solutions. Key-Words: Reinforcement learning, Trajectory sampling, Temporal difference, Working memory, Maze route finding
منابع مشابه
Multicast Routing in Wireless Sensor Networks: A Distributed Reinforcement Learning Approach
Wireless Sensor Networks (WSNs) are consist of independent distributed sensors with storing, processing, sensing and communication capabilities to monitor physical or environmental conditions. There are number of challenges in WSNs because of limitation of battery power, communications, computation and storage space. In the recent years, computational intelligence approaches such as evolutionar...
متن کاملAn Adaptive Learning Game for Autistic Children using Reinforcement Learning and Fuzzy Logic
This paper, presents an adapted serious game for rating social ability in children with autism spectrum disorder (ASD). The required measurements are obtained by challenges of the proposed serious game. The proposed serious game uses reinforcement learning concepts for being adaptive. It is based on fuzzy logic to evaluate the social ability level of the children with ASD. The game adapts itsel...
متن کاملReachability checking in complex and concurrent software systems using intelligent search methods
Software system verification is an efficient technique for ensuring the correctness of a software product, especially in safety-critical systems in which a small bug may have disastrous consequences. The goal of software verification is to ensure that the product fulfills the requirements. Studies show that the cost of finding and fixing errors in design time is less than finding and fixing the...
متن کاملScalable Bayesian Reinforcement Learning for Multiagent POMDPs
Bayesian methods for reinforcement learning (RL) allow model uncertainty to be considered explicitly and offer a principled way of dealing with the exploration/exploitation tradeoff. However, for multiagent systems there have been few such approaches, and none of them apply to problems with state uncertainty. In this paper, we fill this gap by proposing a Bayesian RL framework for multiagent pa...
متن کاملMulti-resolution Exploration in Continuous Spaces
The essence of exploration is acting to try to decrease uncertainty. We propose a new methodology for representing uncertainty in continuous-state control problems. Our approach, multi-resolution exploration (MRE), uses a hierarchical mapping to identify regions of the state space that would benefit from additional samples. We demonstrate MRE’s broad utility by using it to speed up learning in ...
متن کامل