Robotics researcher's bookmark list of Astra evaluations
A robotics reading list covering GPT-6 Astra evaluations on RoboDojo and control tasks, plus posts on data, policy improvement and evaluation.
Here are the must-read in my bookmark. From agentic robotics, policy enhancement, data and eval. 1. Comparison between agentic robotics and Code-as-Policy by @paigeinsf from @se3labs https://x.com/paigeinsf/status/2102871624827760817 2. Evaluation on Astra, Fable and Opus for wetLabs tasks by @joshavata from @meckaai https://x.com/joshavata/status/2103533019172950217 3. Evaluations of GPT-6 Astra on RoboDojo by @_wenbozhang https://x.com/_wenbozhang/status/2106333089140187610 4. Comparison between Astra and Fable on control task by @chooi_jeq from @robocurve https://x.com/chooi_jeq/status/2096064315115839904 5. What matters for policy improvement and what doesn't by @DominiqueCAPaul from @dm_robots https://x.com/DominiqueCAPaul/status/2102825473625465129 6. Argus: An Open‑Source Annotator for Robotics Data by @calixo888 from @PantheonInc https://x.com/calixo888/status/2105697421405917542 7. Robotics data quality, anomalies in opensource datasets by @calixo888 from @pantheoninc https://x.com/calixo888/status/2103160860055109916 8. Eval platform for failure analysis by @charleswongzx from @bifrost_ai https://x.com/charleswongzx/status/2087689841324511522 Please leave in the comments if you have good sharing. I will bookmark it. Thanks!
This post quotes another post: x.com/paigeinsf/status/2102871624827760817