Unsupervised Hebbian Learning on Point Sets in StarCraft II

2022-07-13 · Beomseok Kang, Harshit Kumar, Saurabh Dash, Saibal Mukhopadhyay

Learning the evolution of real-time strategy (RTS) game is a challenging problem in artificial intelligent (AI) system. In this paper, we present a novel Hebbian learning method to extract the global feature of point sets in StarCraft II game units, and its application to predict the movement of the points. Our model includes encoder, LSTM, and decoder, and we train the encoder with the unsupervised learning method. We introduce the concept of neuron activity aware learning combined with k-Winner-Takes-All. The optimal value of neuron activity is mathematically derived, and experiments support the effectiveness of the concept over the downstream task. Our Hebbian learning rule benefits the prediction with lower loss compared to self-supervised learning. Also, our model significantly saves the computational cost such as activations and FLOPs compared to a frame-based approach.

📄 PDF Abstract BibTeX arXiv:2207.12323

Code (0)

등록된 구현이 없습니다.

Tasks

Decoder Self-Supervised LearningStarcraftStarcraft II

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Forecasting Evolution of Clusters in Game Agents with Hebbian Learning

2022-08-19 · Beomseok Kang, Saibal Mukhopadhyay

Large multi-agent systems such as real-time strategy games are often driven by collective behavior of agents. For example, in StarCraft II, human players group spatially near agents into a team and control the team to de…

Clustering Multi-agent Reinforcement Learning Real-Time Strategy Games Self-Supervised Learning+2

Augmenting Supervised Learning by Meta-learning Unsupervised Local Rules

2021-03-17 · NeurIPS Workshop Neuro_AI 2019 12 · Jeffrey Cheng, Ari Benjamin, Benjamin Lansdell, Konrad Paul Kordin

The brain performs unsupervised learning and (perhaps) simultaneous supervised learning. This raises the question as to whether a hybrid of supervised and unsupervised methods will produce better learning. Inspired by th…

Meta-Learning

Unsupervised 3D Object Learning through Neuron Activity aware Plasticity

2023-02-22 · Beomseok Kang, Biswadeep Chakraborty, Saibal Mukhopadhyay

We present an unsupervised deep learning model for 3D object classification. Conventional Hebbian learning, a well-known unsupervised model, suffers from loss of local features leading to reduced performance for tasks wi…

3D Object Classification Object

Deep Features for CBIR with Scarce Data using Hebbian Learning

2022-05-18 · Gabriele Lagani, Davide Bacciu, Claudio Gallicchio, Fabrizio Falchi 외

Features extracted from Deep Neural Networks (DNNs) have proven to be very effective in the context of Content Based Image Retrieval (CBIR). In recent work, biologically inspired \textit{Hebbian} learning algorithms have…

Content-Based Image Retrieval Image Retrieval Retrieval Unsupervised Pre-training

Normative framework for deriving neural networks with multi-compartmental neurons and non-Hebbian plasticity

2023-02-20 · David Lipshutz, Yanis Bahroun, Siavash Golkar, Anirvan M. Sengupta 외

An established normative approach for understanding the algorithmic basis of neural computation is to derive online algorithms from principled computational objectives and evaluate their compatibility with anatomical and…

Self-Supervised Learning