Active Inference in Hebbian Learning Networks
원문 초록
This work studies how brain-inspired neural ensembles equipped with local Hebbian plasticity can perform active inference (AIF) in order to control dynamical agents. A generative model capturing the environment dynamics is learned by a network composed of two distinct Hebbian ensembles: a posterior network, which infers latent states given the observations, and a state transition network, which predicts the next expected latent state given current state-action pairs. Experimental studies are conducted using the Mountain Car environment from the OpenAI gym suite, to study the effect of the various Hebbian network parameters on the task performance. It is shown that the proposed Hebbian AIF approach outperforms the use of Q-learning, while not requiring any replay buffer, as in typical reinforcement learning systems. These results motivate further investigations of Hebbian learning for the design of AIF networks that can learn environment dynamics without the need for revisiting past buffered experiences.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Double Successive Over-Relaxation Q-Learning with an Extension to Deep Reinforcement Learning
Asymptotic Analysis of Sample-averaged Q-learning
Investigating the Performance and Reliability, of the Q-Learning Algorithm in Various Unknown Environments
Q-Learning under Finite Model Uncertainty
Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing
ADDQ: Adaptive Distributional Double Q-Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.