MULTIAGENT LEARNING FOR BLACK BOX SYSTEM REWARD FUNCTIONS
نویسندگان
چکیده
منابع مشابه
Multiagent Learning for Black Box System Reward Functions
In large, distributed systems composed of adaptive and interactive components (agents), ensuring the coordination among the agents so that the system achieves certain performance objectives is a challenging proposition. The key difficulty to overcome in such systems is one of credit assignment: How to apportion credit (or blame) to a particular agent based on the performance of the entire syste...
متن کاملLearning to Learn for Global Optimization of Black Box Functions
We learn recurrent neural network optimizers trained on simple synthetic functions by gradient descent. We show that these learned optimizers exhibit a remarkable degree of transfer in that they can be used to efficiently optimize a broad range of derivative-free black-box functions, including Gaussian process bandits, simple control objectives, global optimization benchmarks and hyper-paramete...
متن کاملReward Functions for Accelerated Learning
This paper discusses why traditional reinforcement learning methods, and algorithms applied to those models, result in poor performance in situated domains characterized by multiple goals, noisy state, and inconsistent reinforcement. We propose a methodology for designing reinforcement functions that take advantage of implicit domain knowledge in order to accelerate learning in such domains. Th...
متن کاملFrom Black-Box Learning Objects to Glass-Box Learning Objects
In the field of e-learning, a popular solution to make teaching material reusable is to represent it as learning object (LO). However, building better adaptive educational software also takes an explicit model of the learner’s cognitive process related to LOs. This paper presents a three layers model that explicitly connect the description of learners’ cognitive processes to LOs. The first laye...
متن کاملLearning in a Black Box ∗
Many interactive environments can be represented as games, but they are so large and complex that individual players are mostly in the dark about others’ actions and the payoff structure. This paper analyzes learning behavior in such ‘black box’ environments, where players’ only source of information is their own history of actions taken and payoffs received. The context of our analysis are dec...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Advances in Complex Systems
سال: 2009
ISSN: 0219-5259,1793-6802
DOI: 10.1142/s0219525909002295