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

arXiv: https://arxiv.org/abs/2102.09361 · HTML: https://mlsanity.com/paper/2102.09361/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 28 references that are in the map.
- First posted on arXiv 18 Feb 2021.

## Builds on (most cited first, 18 of 18)

- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Safe Model-based Reinforcement Learning with Stability Guarantees](https://mlsanity.com/paper/1705.08551/) (2017)
- [Not All Samples Are Created Equal: Deep Learning with Importance Sampling](https://mlsanity.com/paper/1803.00942/) (2018)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [Distral: Robust Multitask Reinforcement Learning](https://mlsanity.com/paper/1707.04175/) (2017)
- [Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning](https://mlsanity.com/paper/1511.06342/) (2015)
- [Multi-task Deep Reinforcement Learning with PopArt](https://mlsanity.com/paper/1809.04474/) (2018)
- [Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees](https://mlsanity.com/paper/1807.03858/) (2018)
- [A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem](https://mlsanity.com/paper/1706.10059/) (2017)
- [Online Batch Selection for Faster Training of Neural Networks](https://mlsanity.com/paper/1511.06343/) (2015)
- [Model-Based Reinforcement Learning via Meta-Policy Optimization](https://mlsanity.com/paper/1809.05214/) (2018)
- [Learning values across many orders of magnitude](https://mlsanity.com/paper/1602.07714/) (2016)
- [Variance Reduction in SGD by Distributed Importance Sampling](https://mlsanity.com/paper/1511.06481/) (2015)
- [PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/1911.00025/) (2019)
- [SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning](https://mlsanity.com/paper/1808.09105/) (2018)
- [Attentive Multi-Task Deep Reinforcement Learning](https://mlsanity.com/paper/1907.02874/) (2019)
- [The Bottleneck Simulator: A Model-based Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1807.04723/) (2018)

## Built on by (most cited first, 3 of 3)

- [WaveCorr: Correlation-savvy Deep Reinforcement Learning for Portfolio Management](https://mlsanity.com/paper/2109.07005/) (2021)
- [Fair Resource Allocation in Weakly Coupled Markov Decision Processes](https://mlsanity.com/paper/2411.09804/) (2024)
- [Fair Policy Optimization in Major-Minor Weakly Coupled Markov Decision Processes](https://mlsanity.com/paper/2609.36174/) (2026)

## Abstract (arXiv)

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.