- dataset: id: ParamTatva/calvin-benchmark task_id: place-in-drawer value: -3.2 date: "2026-02-09" source: url: https://huggingface.co/ParamTatva/R-PPO-SOTA name: R-PPO-SOTA Benchmark Run - dataset: id: ParamTatva/calvin-benchmark task_id: pick-up-block value: -3.6 date: "2026-02-09" source: url: https://huggingface.co/ParamTatva/R-PPO-SOTA name: R-PPO-SOTA Benchmark Run - dataset: id: ParamTatva/calvin-benchmark task_id: turn-on-lightbulb value: -3.7 date: "2026-02-09" source: url: https://huggingface.co/ParamTatva/R-PPO-SOTA name: R-PPO-SOTA Benchmark Run - dataset: id: ParamTatva/calvin-benchmark task_id: close-drawer value: -4.2 date: "2026-02-09" source: url: https://huggingface.co/ParamTatva/R-PPO-SOTA name: R-PPO-SOTA Benchmark Run - dataset: id: ParamTatva/calvin-benchmark task_id: open-drawer value: -6.1 date: "2026-02-09" source: url: https://huggingface.co/ParamTatva/R-PPO-SOTA name: R-PPO-SOTA Benchmark Run