Unobtrusive Workstation Farming Without Inconveniencing Owners: Learning Backgammon with a Genetic Algorithm
نویسنده
چکیده
Most efforts at low-cost parallel computing assume a monopoly on the hardware being used. That all-or-nothing attitude ignores many machines dedicated to other activities, but which sit idle for 16 hours a day. However, naı̈ve attempts to utilize idle machines can interfere with their primary purpose. This paper describes the successful effort to unobtrusively farm idle machines, for an artificial intelligence system using a genetic algorithm to learn the game Backgammon. It maintains owners’ full access to their machines, without causing any detectable interference.
منابع مشابه
A Hybrid Unconscious Search Algorithm for Mixed-model Assembly Line Balancing Problem with SDST, Parallel Workstation and Learning Effect
Due to the variety of products, simultaneous production of different models has an important role in production systems. Moreover, considering the realistic constraints in designing production lines attracted a lot of attentions in recent researches. Since the assembly line balancing problem is NP-hard, efficient methods are needed to solve this kind of problems. In this study, a new hybrid met...
متن کاملNannon: A Nano Backgammon for Machine Learning Research
Nannon is a copyrighted game, but may be used for research and academic purposes. Nannon is a trademark of Nannon Technology corp., which provided permission to publish the rules and board in this paper. AbstractA newly designed game is introduced, which feels like Backgammon, but has a simplified rule set. Unlike earlier attempts at simplifying the game, Nannon maintains enough features and dy...
متن کاملProgramming backgammon using self-teaching neural nets
TD-Gammon is a neural network that is able to teach itself to play backgammon solely by playing against itself and learning from the results. Starting from random initial play, TD-Gammon’s selfteaching methodology results in a surprisingly strong program: without lookahead, its positional judgement rivals that of human experts, and when combined with shallow lookahead, it reaches a level of pla...
متن کاملAchieving Efficient and Cognitively Plausible Learning in Backgammon
Traditionally, computer applications to game domains have taken a brute-force approach, relying on sheer computational power to overcome the complexity of the domain. Although many of these programs have been quite successful, it is interesting to note that humans can still perform extremely well against them. Thus we are compelled to ask, if no human could match the computational power of most...
متن کاملWhy Co-Evolution beats Temporal Difference learning at Backgammon for a linear architecture, but not a non-linear architecture
The No Free Lunch theorems show that the algorithm must suit the problem. This does not answer the novice’s question: for a given problem, which algorithm to use? This paper compares co-evolutionary learning and temporal difference learning on the game of Backgammon, which (like many real-world tasks) has an element of random uncertainty. Unfortunately, to fully evaluate a single strategy using...
متن کامل