AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

First-Person Activity Forecasting With Online Inverse Reinforcement Learning

Nicholas Rhinehart, Kris M. Kitani

ICCV 2017 · Reinforcement learning › Visual and representation RL · approach: Inferring decision-making from behavior · 122 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use stop-based instead of scene-based goal discovery (ablation)Darko · Goal forecasting, labelled actions, Home 1mean true-goal probability: 0.438 -> 0.614Improved
use stop-based instead of scene-based goal discovery (ablation)Darko · Goal forecasting, labelled actions, Office 2mean true-goal probability: 0.238 -> 0.625Improved
use stop-based instead of scene-based goal discovery (ablation)Darko · Goal forecasting, labelled actions, Lab 1mean true-goal probability: 0.426 -> 0.709Improved
use ground-truth labelled detections instead of visual detections (ablation)Darko · Goal forecasting, Home 1mean true-goal probability: 0.524 -> 0.851Improved
add action features to state features in the reward (ablation)Darko with state-only features · Goal forecasting, labelled detections, Home 1mean true-goal probability: 0.735 -> 0.851Improved
add state features to position-only reward features (ablation)Darko with position-only features · Goal forecasting, labelled detections, Home 1mean true-goal probability: 0.674 -> 0.851Improved
use full state-action reward features instead of state only (ablation)Darko · Goal forecasting, labelled detections, Lab 1mean true-goal probability: 0.892 -> 0.880No clear effect
add goal-detection uncertainty (log-probability goal values) (ablation)Darko · Synthetic noisy goal detectionsmean true-goal probabilityImproved
use Darko online IRL instead of logistic regressionLogistic · Goal forecasting, visual detections, Home 1mean true-goal probability: 0.458 -> 0.524Improved
use Darko online IRL instead of RNNRNN · Goal forecasting, visual detections, Lab 1mean true-goal probability: 0.455 -> 0.473Improved
use Darko trajectory length forecast instead of nearest neighborsNearest neighbors · Trajectory length, Office 1median % error: 42.9 -> 17.3Improved
use Darko trajectory length forecast instead of nearest neighborsNearest neighbors · Trajectory length, Home 1median % error: 29.0 vs 30.0No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy