The effectiveness of the BFM-QD framework is shown, benefiting from the synergy between dimensionality reduction of the search space and offline pretraining from diverse behavioral data, which positions BFMs as a general-purpose backbone for QD optimization.
Nazim Bendib, Nicolas Perrin-Gilbert, Olivier Sigaud· arXiv.org· 0 citations
An open-source sim-to-real experimental protocol that addresses this bottleneck: expert trajectories generated in simulation are replayed open-loop on a real Franka FR3 setup, where the corresponding real visual and proprioceptive observations are recorded and converted into a format compatible with VLA training.
Mathilde Kappel, Clémence Grislain, Mohamed Chetouani et al.· 0 citations
An alternative reward shaping method (RS) is proposed that removes deceptive rewards at the expense of theoretical guarantees of PBRS, and another method named Locally-Guided Actor Critic (LG-AC) that rewards the agent for reaching intermediate goals achieves the best overall performance across tasks.