AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Younggyo Seo, Kimin Lee, Ignasi Clavera Gilaberte, Thanard Kurutach, Jinwoo Shin, Pieter Abbeel

NeurIPS 2020 · Reinforcement learning › Visual and representation RL · approach: Latent-space world models · 7 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 trajectory-wise oracle loss rather than single-transition MCL (ablation)Multi-headed dynamics model · Unseen control environmentsgeneralization performanceImproved
Add adaptive selection of the best prediction head instead of averaging head predictions (ablation)T-MCL · Unseen control environmentsaverage returnImproved
Add context learning to the multi-headed dynamics model (ablation)T-MCL · Unseen HalfCheetah environmentsgeneralization performanceImproved
Use a multi-headed architecture without trajectory-wise oracle loss, context learning, or adaptive planning (ablation)PETS · Unseen HalfCheetah environmentsgeneralization performanceNo clear effect
Increase prediction-head count above 3 (ablation)T-MCL · Unseen HalfCheetah environmentsgeneralization performanceHurt
Use more transitions in the trajectory-wise oracle loss (ablation)T-MCL · Unseen control environmentsgeneralization performanceImproved
Use more transitions for adaptive planning (ablation)T-MCL · Unseen control environmentsgeneralization performanceImproved
Use T-MCL instead of PETSModel-based RL · HalfCheetah unseen environmentsaverage return: 2223.9 -> 19280.1Improved
Use T-MCL instead of CaDMModel-based RL · CrippledAntaverage return: 3.5xImproved

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