3/7 Experiment Setup
We compare three quality-aware approaches: weighting, filtering, and conditioning, across two reward definitions (object-centric and approach-aware) and two label granularities (episode and action chunk).
The controlled study uses 5,000 simulation https://t.co/ATyOleyayw
We compare three quality-aware approaches: weighting, filtering, and conditioning, across two reward definitions (object-centric and approach-aware) and two label granularities (episode and action chunk).
The controlled study uses 5,000 simulation https://t.co/ATyOleyayw