AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Assessing Transferability From Simulation to Reality for Reinforcement Learning

Fabio Muratore, Michael Gienger, Jan Peters

TPAMI 2019 · Reinforcement learning › Visual and representation RL · approach: Skill learning and diffusion policies · 74 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 domain randomization (SPOTA or EPOpt) instead of plain PPO on nominal modelPPO · Ball-Balancer sim-to-realtransfer success: failed in all but 2 trials -> most trials transferImproved
add domain randomization (SPOTA or EPOpt) instead of plain PPO on nominal modelPPO · Cart-Pole sim-to-realtransfer success: failed in all trials -> most trials transferImproved
add domain randomization instead of nominal-only trainingPPO · Ball-Balancer and Cart-Pole sim-to-simrobustness to parameter changesImproved
use CVaR-based objective (EPOpt) instead of expected returnEPOpt · Sim-to-simnominal-domain performanceHurt
add domain randomization instead of nominal trainingPPO · Sim-to-simvariance of returnsImproved
increase number of domains during SPOTA iterations (ablation)SPOTA · Ball-Balancer (simulated)UCBOGImproved
increase number of domains n in illustrative example (ablation)Optimal policy for n domains · Illustrative catapult examplesimulation optimization biasImproved

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