paper-with-me

Papers

How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation

2021-02-08 · Augustine N. Mavor-Parker, Kimberly A. Young, Caswell Barry, Lewis D. Griffin

Exploration in environments with sparse rewards is difficult for artificial agents. Curiosity driven learning -- using feed-forward prediction errors as intrinsic rewards -- has achieved some success in these scenarios, but fails when faced with action-dependent noise sources. We present aleatoric mapping agents (AMAs), a neuroscience inspired solution modeled on the cholinergic system of the mammalian brain. AMAs aim to explicitly ascertain which dynamics of the environment are unpredictable, regardless of whether those dynamics are induced by the actions of the agent. This is achieved by generating separate forward predictions for the mean and variance of future states and reducing intrinsic rewards for those transitions with high aleatoric variance. We show AMAs are able to effectively circumvent action-dependent stochastic traps that immobilise conventional curiosity driven agents. The code for all experiments presented in this paper is open sourced: http://github.com/self-supervisor/Escaping-Stochastic-Traps-With-Aleatoric-Mapping-Agents.

📄 PDF Abstract BibTeX arXiv:2102.04399

Code (2)

self-supervisor/escaping-stochastic-traps-with-aleatoric-mapping-agents 공식 구현 tf
self-supervisor/how_to_stay_curious_while_avoiding_noisy_tvs 공식 구현 tf

Similar Papers 제목 키워드 기반

B-PINNs: Bayesian Physics-Informed Neural Networks for Forward and Inverse PDE Problems with Noisy Data

2020-03-13 · Liu Yang, Xuhui Meng, George Em. Karniadakis

We propose a Bayesian physics-informed neural network (B-PINN) to solve both forward and inverse nonlinear problems described by partial differential equations (PDEs) and noisy data. In this Bayesian framework, the Bayes…

Uncertainty QuantificationVariational Inference

Uncertainty-aware Human Mobility Modeling and Anomaly Detection

2024-10-02 · Haomin Wen, Shurui Cao, Zeeshan Rasheed, Khurram Hassan Shafique 외

Given the temporal GPS coordinates from a large set of human agents, how can we model their mobility behavior toward effective anomaly (e.g. bad-actor or malicious behavior) detection without any labeled data? Human mobi…

Anomaly DetectionDecision MakingTrajectory Modeling

Variational LSTM with Augmented Inputs: Nonlinear Response History Metamodeling with Aleatoric and Epistemic Uncertainty

2026-04-02 · Manisha Sapkota, Min Li, Bowei Li arxiv

Uncertainty propagation in high-dimensional nonlinear dynamic structural systems is pivotal in state-of-the-art performance-based design and risk assessment, where uncertainties from both excitations and structures, i.e.…

Neighborhood Spatial Aggregation MC Dropout for Efficient Uncertainty-aware Semantic Segmentation in Point Clouds

2021-12-05 · Chao Qi, Jianqin Yin

Uncertainty-aware semantic segmentation of the point clouds includes the predictive uncertainty estimation and the uncertainty-guided model optimization. One key challenge in the task is the efficiency of point-wise pred…

Model OptimizationSemantic Segmentation

The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals

2020-11-03 · Takumi Kawashima, Qing Yu, Akari Asai, Daiki Ikami 외

We propose a new optimization framework for aleatoric uncertainty estimation in regression problems. Existing methods can quantify the error in the target estimation, but they tend to underestimate it. To obtain the pred…

Age EstimationDepth Estimationregression