Portrait de Charlotte Cloutier

Charlotte Cloutier

Maîtrise recherche - UdeM
Superviseur⋅e principal⋅e
Sujets de recherche
Apprentissage par renforcement
IA et durabilité
Robotique

Publications

Finetuning VLAs for Dexterous Manipulation: The Right Checkpoint Is All You Need
Vision-Language-Action models have demonstrated strong manipulation capabilities. A limitation of VLA models is that most manipulation datas… (voir plus)ets focus on parallel-jaw gripper systems, making transfer to multi-finger hands challenging, particularly as teleoperation datasets are harder to collect with multi-fingered robots. In this work, we study how to best adapt VLAs to dexterous hands by pairing supervised fine-tuning (SFT) with diffusion-steering reinforcement learning (DSRL). Using
Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
Behavioral cloning (BC) methods trained with supervised learning (SL) are an effective way to learn policies from human demonstrations in do… (voir plus)mains like robotics. Goal-conditioning these policies enables a single generalist policy to capture diverse behaviors contained within an offline dataset. While goal-conditioned behavior cloning (GCBC) methods can perform well on in-distribution training tasks, they do not necessarily generalize zero-shot to tasks that require conditioning on novel state-goal pairs, i.e. combinatorial generalization. In part, this limitation can be attributed to a lack of temporal consistency in the state representation learned by BC; if temporally related states are encoded to similar latent representations, then the out-of-distribution gap for novel state-goal pairs would be reduced. Hence, encouraging this temporal consistency in the representation space should facilitate combinatorial generalization. Successor representations, which encode the distribution of future states visited from the current state, nicely encapsulate this property. However, previous methods for learning successor representations have relied on contrastive samples, temporal-difference (TD) learning, or both. In this work, we propose a simple yet effective representation learning objective,