Zero-Shot Reinforcement Learning via Function Encoders
Although reinforcement learning (RL) can solve many challenging sequential decision making problems, achieving zero-shot transfer across related tasks remains a challenge. The difficulty lies in finding a good representation for the current task so that the agent understands how it relates to previously seen tasks. To achieve zero-shot transfer, we introduce the function encoder, a representation learning algorithm which represents a function as a weighted combination of learned, non-linear basis functions. By using a function encoder to represent the reward function or the transition function, the agent has information on how the current task relates to previously seen tasks via a coherent vector representation. Thus, the agent is able to achieve transfer between related tasks at run time with no additional training. We demonstrate state-of-the-art data efficiency, asymptotic performance, and training stability in three RL fields by augmenting basic RL algorithms with a function encoder task representation.
Code (2)
Tasks
Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Representation LearningSequential Decision MakingSimilar Papers 제목 키워드 기반
TD-JEPA: Latent-predictive Representations for Zero-Shot Reinforcement Learning
Latent prediction--where agents learn by predicting their own latents--has emerged as a powerful paradigm for training general representations in machine learning. In reinforcement learning (RL), this approach has been e…
Reinforcement LearningDoes Zero-Shot Reinforcement Learning Exist?
A zero-shot RL agent is an agent that can solve any RL task in a given environment, instantly with no additional planning or learning, after an initial reward-free learning phase. This marks a shift from the reward-centr…
Contrastive Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1Cross-Linked Variational Autoencoders for Generalized Zero-Shot Learning
Most approaches in generalized zero-shot learning rely on cross-modal mapping between an image feature space and a class embedding space or on generating artificial image features. However, learning a shared cross-modal …
Few-Shot LearningGeneralized Zero-Shot LearningZero-Shot LearningZoom-shot: Fast and Efficient Unsupervised Zero-Shot Transfer of CLIP to Vision Encoders with Multimodal Loss
The fusion of vision and language has brought about a transformative shift in computer vision through the emergence of Vision-Language Models (VLMs). However, the resource-intensive nature of existing VLMs poses a signif…
Knowledge Distillationzero-shot-classificationZero-Shot LearningLimitations of Knowledge Distillation for Zero-shot Transfer Learning
Pretrained transformer-based encoders such as BERT have been demonstrated to achieve state-of-the-art performance on numerous NLP tasks. Despite their success, BERT style encoders are large in size and have high latency …
CPUCross-Lingual TransferKnowledge DistillationTransfer Learning+1