Mutual Alignment Transfer Learning
Training robots for operation in the real world is a complex, time consuming and potentially expensive task. Despite significant success of reinforcement learning in games and simulations, research in real robot applications has not been able to match similar progress. While sample complexity can be reduced by training policies in simulation, such policies can perform sub-optimally on the real platform given imperfect calibration of model dynamics. We present an approach -- supplemental to fine tuning on the real robot -- to further benefit from parallel access to a simulator during training and reduce sample requirements on the real robot. The developed approach harnesses auxiliary rewards to guide the exploration for the real world agent based on the proficiency of the agent in simulation and vice versa. In this context, we demonstrate empirically that the reciprocal alignment for both agents provides further benefit as the agent in simulation can adjust to optimize its behaviour for states commonly visited by the real-world agent.
Code (0)
등록된 구현이 없습니다.
Tasks
Reinforcement LearningTransfer LearningSimilar Papers 제목 키워드 기반
InfoCLIP: Bridging Vision-Language Pretraining and Open-Vocabulary Semantic Segmentation via Information-Theoretic Alignment Transfer
Recently, the strong generalization ability of CLIP has facilitated open-vocabulary semantic segmentation, which labels pixels using arbitrary text. However, existing methods that fine-tune CLIP for segmentation on limit…
Semantic SegmentationMutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning
This paper investigates cross-lingual temporal knowledge graph reasoning problem, which aims to facilitate reasoning on Temporal Knowledge Graphs (TKGs) in low-resource languages by transfering knowledge from TKGs in hig…
Knowledge DistillationKnowledge GraphsTransfer LearningFedMKT: Federated Mutual Knowledge Transfer for Large and Small Language Models
Recent research in federated large language models (LLMs) has primarily focused on enabling clients to fine-tune their locally deployed homogeneous LLMs collaboratively or on transferring knowledge from server-based LLMs…
Text GenerationTransfer LearningImage-to-Video Re-Identification via Mutual Discriminative Knowledge Transfer
The gap in representations between image and video makes Image-to-Video Re-identification (I2V Re-ID) challenging, and recent works formulate this problem as a knowledge distillation (KD) process. In this paper, we propo…
Knowledge DistillationTransfer LearningTripletLLaVAFlow: Preserving Latent Alignment Flow for Parameter-Efficient Multimodal Fine-Tuning
While Multimodal Large Language Models (MLLMs) exhibit strong generalization, visual instruction tuning for downstream tasks inevitably causes catastrophic forgetting, impairing overall generalization. While existing met…