اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدAn Evolutionary Algorithm for Error-Driven Learning via Reinforcement
413
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Although different learning systems are coordinated to afford complex behavior, little is known about how this occurs. This article describes a theoretical framework that specifies how complex behaviors that might be thought to require error-driven learning might instead be acquired through simple reinforcement. This framework includes specific assumptions about the mechanisms that contribute to the evolution of (artificial) neural networks to generate topologies that allow the networks to learn large-scale complex problems using only information about the quality of their performance. The practical and theoretical implications of the framework are discussed, as are possible biological analogs of the approach.
قيم البحث
اقرأ أيضاً
Many real-world applications involve teams of agents that have to coordinate their actions to reach a common goal against potential adversaries. This paper focuses on zero-sum games where a team of players faces an opponent, as is the case, for examp
le, in Bridge, collusion in poker, and collusion in bidding. The possibility for the team members to communicate before gameplay---that is, coordinate their strategies ex ante---makes the use of behavioral strategies unsatisfactory. We introduce Soft Team Actor-Critic (STAC) as a solution to the teams coordination problem that does not require any prior domain knowledge. STAC allows team members to effectively exploit ex ante communication via exogenous signals that are shared among the team. STAC reaches near-optimal coordinated strategies both in perfectly observable and partially observable games, where previous deep RL algorithms fail to reach optimal coordinated behaviors.
AI systems are increasingly applied to complex tasks that involve interaction with humans. During training, such systems are potentially dangerous, as they havent yet learned to avoid actions that could cause serious harm. How can an AI system explor
e and learn without making a single mistake that harms humans or otherwise causes serious damage? For model-free reinforcement learning, having a human in the loop and ready to intervene is currently the only way to prevent all catastrophes. We formalize human intervention for RL and show how to reduce the human labor required by training a supervised learner to imitate the humans intervention decisions. We evaluate this scheme on Atari games, with a Deep RL agent being overseen by a human for four hours. When the class of catastrophes is simple, we are able to prevent all catastrophes without affecting the agents learning (whereas an RL baseline fails due to catastrophic forgetting). However, this scheme is less successful when catastrophes are more complex: it reduces but does not eliminate catastrophes and the supervised learner fails on adversarial examples found by the agent. Extrapolating to more challenging environments, we show that our implementation would not scale (due to the infeasible amount of human labor required). We outline extensions of the scheme that are necessary if we are to train model-free agents without a single catastrophe.
Psychlab is a simulated psychology laboratory inside the first-person 3D game world of DeepMind Lab (Beattie et al. 2016). Psychlab enables implementations of classical laboratory psychological experiments so that they work with both human and artifi
cial agents. Psychlab has a simple and flexible API that enables users to easily create their own tasks. As examples, we are releasing Psychlab implementations of several classical experimental paradigms including visual search, change detection, random dot motion discrimination, and multiple object tracking. We also contribute a study of the visual psychophysics of a specific state-of-the-art deep reinforcement learning agent: UNREAL (Jaderberg et al. 2016). This study leads to the surprising conclusion that UNREAL learns more quickly about larger target stimuli than it does about smaller stimuli. In turn, this insight motivates a specific improvement in the form of a simple model of foveal vision that turns out to significantly boost UNREALs performance, both on Psychlab tasks, and on standard DeepMind Lab tasks. By open-sourcing Psychlab we hope to facilitate a range of future such studies that simultaneously advance deep reinforcement learning and improve its links with cognitive science.
We introduce ES-ENAS, a simple yet general evolutionary joint optimization procedure by combining continuous optimization via Evolutionary Strategies (ES) and combinatorial optimization via Efficient NAS (ENAS) in a highly scalable and intuitive way.
Our main insight is noticing that ES is already a highly distributed algorithm involving hundreds of forward passes which can not only be used for training neural network weights, but also for jointly training a NAS controller, both in a blackbox fashion. By doing so, we also bridge the gap from NAS research in supervised learning settings to the reinforcement learning scenario through this relatively simple marriage between two different yet common lines of research. We demonstrate the utility and effectiveness of our method over a large search space by training highly combinatorial neural network architectures for RL problems in continuous control, via edge pruning and quantization. We also incorporate a wide variety of popular techniques from modern NAS literature including multiobjective optimization along with various controller methods, to showcase their promise in the RL field and discuss possible extensions.
In this paper we propose a novel method for learning how algorithms perform. Classically, algorithms are compared on a finite number of existing (or newly simulated) benchmark datasets based on some fixed metrics. The algorithm(s) with the smallest v
alue of this metric are chosen to be the `best performing. We offer a new approach to flip this paradigm. We instead aim to gain a richer picture of the performance of an algorithm by generating artificial data through genetic evolution, the purpose of which is to create populations of datasets for which a particular algorithm performs well on a given metric. These datasets can be studied so as to learn what attributes lead to a particular progression of a given algorithm. Following a detailed description of the algorithm as well as a brief description of an open source implementation, a case study in clustering is presented. This case study demonstrates the performance and nuances of the method which we call Evolutionary Dataset Optimisation. In this study, a number of known properties about preferable datasets for the clustering algorithms known as (k)-means and DBSCAN are realised in the generated datasets.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
