AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

R2P2: A ReparameteRized Pushforward Policy for Diverse, Precise Generative Path Forecasting

Nicholas Rhinehart, Kris M. Kitani, Paul Vernaza

ECCV 2018 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 214 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
add prior-cost term beta=0.1 (H(q,p~)) to training objective (ablation)R2P2 RNN · CaliForecasting (K=12)Test -H(q_theta, p~): -125.0 -> -119.0Improved
add prior-cost term beta=0.1 (ablation)R2P2 Field · CaliForecasting (K=12)Test -H(q_theta, p~): -142.5 -> -132.8Improved
add prior-cost term beta=0.1 (ablation)R2P2 Linear · CaliForecasting (K=12)Test -H(q_theta, p~): -144.5 -> -134.1Improved
add prior-cost term beta=0.1 (ablation)R2P2 RNN · CaliForecasting (K=12)Test -H(p, q_theta): 70.20 -> 66.89Hurt
add prior-cost term beta=0.1 (ablation)R2P2 Linear · CaliForecasting (K=12)Test -H(p, q_theta): 64.02 -> 61.57Hurt
add prior-cost term beta=0.3 (ablation)R2P2 RNN · Kitti (K=12)Test minMSD: 1.574 -> 1.282Improved
use R2P2 reparameterized pushforward objective instead of standard GAILGAIL-WG · CaliForecasting (K=12)Test -H(p, q_theta): 27.43 -> 45.55Improved
use R2P2 reparameterized pushforward objective instead of standard GAILGAIL-WG · Kitti (K=12)Test -H(p, q_theta): 39.53 -> 47.45Improved
use R2P2 RNN instead of CVAECVAE · CaliForecasting (K=12)Test minMSD: 1.680 -> 1.530Hurt
use CNN discriminator instead of MLP discriminator (ablation)R2P2 GAIL-WG · CaliForecasting (K=12)Test -H(p, q_theta): 45.55 -> 43.55Hurt
use RNN policy instead of linear policy (ablation)R2P2 · CaliForecasting (K=12)Test -H(p, q_theta): 64.02 -> 70.20Improved
use R2P2 instead of GAIL in the cross trimodal domainGAIL · Cross trimodalTest -H(p, q_theta): 14.10 -> 40.79Improved

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