AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Cross-modal Domain Adaptation for Cost-Efficient Visual Reinforcement Learning

Xiong-Hui Chen, Shengyi Jiang, Feng Xu, Zongzhang Zhang, Yang Yu

NeurIPS 2021 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 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
replace MLP mapping function with RNN mapping function (ablation)CODAS · Hopper and Inverted Double Pendulumreward ratioImproved
feed trajectories into the discriminator (RNN-N to RNN-Y) (ablation)CODAS · Inverted Double Pendulum and Walker2dreward ratioImproved
add embedded-DM to RNN mapping (RNN-Y to DM-RNN-Y) (ablation)CODAS · Hopper, Inverted Double Pendulum, Walker2dreward ratioImproved
add cycle-consistent loss to GAN (CycleGAN vs GAN) (ablation)GAN baseline · MuJoCo tasksreward ratioNo clear effect
stack input frames in GAN (GAN STACK vs GAN)GAN baseline · MuJoCo tasksreward ratioMixed
increase friction in source domain to 2.0x (dynamics mismatch) (ablation)CODAS · Hopperreward ratioHurt
increase friction in source domain to 1.2x and 1.6x (ablation)CODAS · Hopperreward ratioNo clear effect
degrade data-collecting policy to 77% and 46% of original performance (policy mismatch) (ablation)CODAS · Hopperreward ratioHurt
goal-conditional relocate task instead of other hand tasksCODAS · Hand manipulationreward ratio: 0.886 -> 0.090Hurt
use CODAS rather than GAN or CycleGAN with cross-modal mappingCODAS · MuJoCo tasksreward ratioImproved
use CODAS rather than baselines for state mappingCODAS · MuJoCo tasksRMSE of mapped statesImproved
behavior cloning versus domain adaptation in HalfCheetahBC · HalfCheetahreward ratioMixed

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