Efficient Reinforcement Learning In Resource Allocation Problems Through Permutation Invariant Multi-task Learning

Abstract

One of the main challenges in real-world reinforcement learning is to learn successfully from limited training samples. We show that in certain settings, the available data can be dramatically increased through a form of multi-task learning, by exploiting an invariance property in the tasks. We provide a theoretical performance bound for the gain in sample efficiency under this setting. This motivates a new approach to multi-task learning, which involves the design of an appropriate neural network architecture and a prioritized task-sampling strategy. We demonstrate empirically the effectiveness of the proposed approach on two real-world sequential resource allocation tasks where this invariance property occurs: financial portfolio optimization and meta federated learning.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keycai2021efficient

Related papers

• A Model-based Approach For Sample-efficient Multi-task Reinforcement Learning (2019)0.00
• A Multi-task Approach To Robust Deep Reinforcement Learning For Resource Allocation (2023)0.00
• Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning With Diverse Tasks (2024)0.00
• Shared-unique Features And Task-aware Prioritized Sampling On Multi-task Reinforcement Learning (2024)0.00
• A Decentralized Policy Gradient Approach To Multi-task Reinforcement Learning (2020)0.00
• Provable Benefit Of Multitask Representation Learning In Reinforcement Learning (2022)0.00
• Permutation Invariant Policy Optimization For Mean-field Multi-agent Reinforcement Learning: A Principled Approach (2021)0.00
• Double Meta-learning For Data Efficient Policy Optimization In Non-stationary Environments (2020)0.00