AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Sim and Real: Better Together

Shirli Di-Castro Shashua, Dotan Di Castro, Shie Mannor

NeurIPS 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Imitation and skill learning · 4 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
Train only on simulation samplesDDPG + HER on Fetch Push · Fetch Push, real environmentsuccess rateHurt
Use mixed sim and real training with q_r=0.1 rather than real-only trainingDDPG + HER on Fetch Push · Fetch Push, real environmentreal episodes to reach 0.9 success rate: 20K -> ≈10KImproved
Increase the real-data collection probability across intermediate q_r values (ablation)Mixed sim-real training on Fetch Push · Fetch Push, real environmentsuccess rateHurt
Set real replay-buffer sampling probability equal to its collection probability (q_r=0.1, beta_r=0.1) (ablation)Mixed sim-real training on Fetch Push · Fetch Push, real environmentsuccess rateHurt
Raise beta_r above q_r, to beta_r=0.3, 0.5, or 0.7 (ablation)Mixed sim-real training on Fetch Push · Fetch Push, real environmentsuccess rateImproved
Set beta_r=0.9 while q_r=0.1 (ablation)Mixed sim-real training on Fetch Push · Fetch Push, real environmentsuccess rateHurt
Use Sim-dependent training: start with sim-only, then switch to mixed training after sim success reaches 0.7 (ablation)DDPG + HER on Fetch Push · Fetch Push, real environmentreal episodes to reach 0.9 success rateImproved
Use Sim first: start with sim-only, then switch to real-only after sim success reaches 0.7 (ablation)DDPG + HER on Fetch Push · Fetch Push, real environmentreal episodes to reach 0.9 success rateHurt
Apply mixed training after transferring a simulation-trained policy to the real environment instead of switching to real-only (ablation)DDPG + HER on Fetch Push · Fetch Push, real environmentreal episodesImproved

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