paper-with-me

홈 › Papers

Dynamic Neural Curiosity Enhances Learning Flexibility for Autonomous Goal Discovery

2024-11-29 · Quentin Houbre, Roel Pieters

The autonomous learning of new goals in robotics remains a complex issue to address. Here, we propose a model where curiosity influence learning flexibility. To do so, this paper proposes to root curiosity and attention together by taking inspiration from the Locus Coeruleus-Norepinephrine system along with various cognitive processes such as cognitive persistence and visual habituation. We apply our approach by experimenting with a simulated robotic arm on a set of objects with varying difficulty. The robot first discovers new goals via bottom-up attention through motor babbling with an inhibition of return mechanism, then engage to the learning of goals due to neural activity arising within the curiosity mechanism. The architecture is modelled with dynamic neural fields and the learning of goals such as pushing the objects in diverse directions is supported by the use of forward and inverse models implemented by multi-layer perceptrons. The adoption of dynamic neural fields to model curiosity, habituation and persistence allows the robot to demonstrate various learning trajectories depending on the object. In addition, the approach exhibits interesting properties regarding the learning of similar goals as well as the continuous switch between exploration and exploitation.

📄 PDF Abstract BibTeX arXiv:2412.00152

Code (1)

rouzinho/Dynamic-Neural-Curiosity 공식 구현

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Curiosity & Entropy Driven Unsupervised RL in Multiple Environments

2024-01-08 · Shaurya Dewan, Anisha Jain, Zoe LaLena, Lifan Yu

The authors of 'Unsupervised Reinforcement Learning in Multiple environments' propose a method, alpha-MEPOL, to tackle unsupervised RL across multiple environments. They pre-train a task-agnostic exploration policy using…

Unsupervised Reinforcement Learning

Curriculum-guided Hindsight Experience Replay

2019-12-01 · NeurIPS 2019 12 · Meng Fang, Tianyi Zhou, Yali Du, Lei Han 외

In off-policy deep reinforcement learning, it is usually hard to collect sufficient successful experiences with sparse rewards to learn from. Hindsight experience replay (HER) enables an agent to learn from failures by t…

Deep Reinforcement LearningDiversityReinforcement Learning

Curiosity-Driven Reinforcement Learning based Low-Level Flight Control

2023-07-28 · Amir Ramezani Dooraki, Alexandros Iosifidis

Curiosity is one of the main motives in many of the natural creatures with measurable levels of intelligence for exploration and, as a result, more efficient learning. It makes it possible for humans and many animals to …

reinforcement-learningReinforcement Learning

Curiosity Driven Exploration of Learned Disentangled Goal Spaces

2018-07-04 · Adrien Laversanne-Finot, Alexandre Péré, Pierre-Yves Oudeyer

Intrinsically motivated goal exploration processes enable agents to autonomously sample goals to explore efficiently complex environments with high-dimensional continuous actions. They have been applied successfully to r…

DiversityEfficient ExplorationRepresentation Learning

Curiosity as filling, compressing, and reconfiguring knowledge networks

2022-04-03 · Shubhankar P. Patankar, Dale Zhou, Christopher W. Lynn, Jason Z. Kim 외

Due to the significant role that curiosity plays in our lives, several theoretical constructs, such as the information gap theory and compression progress theory, have sought to explain how we engage in its practice. Acc…