Zero-shot Reinforcement Learning Via Function Encoders

Abstract

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 encod

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyingebrand2024zero

Related papers

• Cross-trajectory Representation Learning For Zero-shot Generalization In RL (2021)0.00
• A Unified Framework For Zero-shot Reinforcement Learning (2025)0.00
• Does Zero-shot Reinforcement Learning Exist? (2022)0.00
• On Zero-shot Reinforcement Learning (2025)0.00
• Hypernetworks For Zero-shot Transfer In Reinforcement Learning (2022)6.34
• Pixel To Policy: DQN Encoders For Within & Cross-game Reinforcement Learning (2023)0.00
• Zero-shot Reinforcement Learning From Low Quality Data (2023)0.00
• Improving Sample Efficiency In Model-free Reinforcement Learning From Images (2019)16.99