First-Person Activity Forecasting with Online Inverse Reinforcement Learning

2016-12-22 · ICCV 2017 10 · Nicholas Rhinehart, Kris M. Kitani

We address the problem of incrementally modeling and forecasting long-term goals of a first-person camera wearer: what the user will do, where they will go, and what goal they seek. In contrast to prior work in trajectory forecasting, our algorithm, DARKO, goes further to reason about semantic states (will I pick up an object?), and future goal states that are far in terms of both space and time. DARKO learns and forecasts from first-person visual observations of the user's daily behaviors via an Online Inverse Reinforcement Learning (IRL) approach. Classical IRL discovers only the rewards in a batch setting, whereas DARKO discovers the states, transitions, rewards, and goals of a user from streaming data. Among other results, we show DARKO forecasts goals better than competing methods in both noisy and ideal settings, and our approach is theoretically and empirically no-regret.

📄 PDF Abstract BibTeX arXiv:1612.07796

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Trajectory Forecasting

Multimodal Physical Activity Forecasting in Free-Living Clinical Settings: Hunting Opportunities for Just-in-Time Interventions

2024-10-12 · Abdullah Mamun, Krista S. Leonard, Megan E. Petrov, Matthew P. Buman 외

Objective: This research aims to develop a lifestyle intervention system, called MoveSense, that forecasts a patient's activity behavior to allow for early and personalized interventions in real-world clinical environmen…

regression Time Series Forecasting

Improved Activity Forecasting for Generating Trajectories

2019-12-12 · Daisuke Ogawa, Toru Tamaki, Tsubasa Hirakawa, Bisser Raytchev 외

An efficient inverse reinforcement learning for generating trajectories is proposed based of 2D and 3D activity forecasting. We modify reward function with $L_p$ norm and propose convolution into value iteration steps, w…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Inverse Moment Methods for Sufficient Forecasting using High-Dimensional Predictors

2017-05-01 · Wei Luo, Lingzhou Xue, Jiawei Yao, Xiufan Yu

We consider forecasting a single time series using a large number of predictors in the presence of a possible nonlinear forecast function. Assuming that the predictors affect the response through the latent factors, we p…

Dimensionality Reduction Model Selection Time Series Time Series Analysis+1

AdaptStress: Online Adaptive Learning for Interpretable and Personalized Stress Prediction Using Multivariate and Sparse Physiological Signals

2026-02-19 · Xueyi Wang, Claudine J. C. Lamoth, Elisabeth Wilhelm arxiv

Continuous stress forecasting could potentially contribute to lifestyle interventions. This paper presents a novel, explainable, and individualized approach for stress prediction using physiological data from consumer-gr…

Time Series Forecasting

Generalizable Implicit Neural Representations via Parameterized Latent Dynamics for Baroclinic Ocean Forecasting

2025-03-27 · Guang Zhao, Xihaier Luo, Seungjun Lee, Yihui Ren 외

Mesoscale ocean dynamics play a critical role in climate systems, governing heat transport, hurricane genesis, and drought patterns. However, simulating these processes at high resolution remains computationally prohibit…

Computational Efficiency