RACE: Calibrated Cumulative Scoring for Rollout-Free Robot Policy Checkpoint Selection
cs.RO, cs.AI, cs.LG
Submitted: 2026-11-04
Updated: 2026-11-04
Code: https://github.com/droid-dataset/droid_policy_learning3https:
Terminology
Sources
- Reliable and Scalable Robot Policy Evaluation with Imperfect Simulators
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- PolaRiS: Scalable Real-to-Sim Evaluations for Generalist Robot Policies
- Batch Policy Learning under Constraints
- WorldEval: World Model as Real-World Robot Policies Evaluator
- Hyperparameter Selection for Offline Reinforcement Learning
- WorldGym: World Model as An Environment for Policy Evaluation
- Is Your Imitation Learning Policy Better than Mine? Policy Comparison with Near-Optimal Stopping
- Beyond Binary Success: Sample-Efficient and Statistically Rigorous Robot Policy Comparison
- Feedback in Imitation Learning: The Three Regimes of Covariate Shift
- Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer
- Gemini Robotics: Bringing AI into the Physical World
- Interactive World Simulator for Robot Policy Training and Evaluation
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation