AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction

Michael Janner, Igor Mordatch, Sergey Levine

NeurIPS 2020 · Probabilistic and scientific modeling › Dynamical systems · approach: Latent-space control and planning · 5 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
increase training discount gamma from 0 to 0.95 (ablation)flow gamma-model · Acrobot and pendulum predictionpredictive lookahead (qualitative)Improved
use normalizing flow instead of GAN parameterization (ablation)gamma-model · Acrobot and pendulum predictionprediction reliability (qualitative)Improved
use gamma-model for value estimation instead of single-step model rolloutsvalue estimation · Pendulum, gamma=0.99rollout steps: 299-step rollouts -> single feedforward passImproved
replace SAC value estimation with gamma-MVESAC · Continuous control benchmarkssample efficiencyImproved
original GAN vs least-squares GAN objective (ablation)GAN gamma-model · gamma-model trainingtraining effectivenessNo 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