Generating Auxiliary Tasks with Reinforcement Learning

• URL: http://arxiv.org/abs/2510.22940v4
• Date: Mon, 03 Nov 2025 23:55:55 GMT
• Title: Generating Auxiliary Tasks with Reinforcement Learning
• Authors: Judah Goldfeder, Matthew So, Hod Lipson,
• Abstract summary: Auxiliary Learning (AL) is a form of multi-task learning in which a model trains on auxiliary tasks to boost performance on a primary objective.<n>We propose RL-AUX, a reinforcement-learning framework that dynamically creates auxiliary tasks by assigning auxiliary labels to each training example.<n>On CIFAR-100 grouped into 20 superclasses, our RL method outperforms human-labeled auxiliary tasks and matches the performance of a prominent bi-level optimization baseline.
• Score: 5.948273590155768
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Auxiliary Learning (AL) is a form of multi-task learning in which a model trains on auxiliary tasks to boost performance on a primary objective. While AL has improved generalization across domains such as navigation, image classification, and NLP, it often depends on human-labeled auxiliary tasks that are costly to design and require domain expertise. Meta-learning approaches mitigate this by learning to generate auxiliary tasks, but typically rely on gradient based bi-level optimization, adding substantial computational and implementation overhead. We propose RL-AUX, a reinforcement-learning (RL) framework that dynamically creates auxiliary tasks by assigning auxiliary labels to each training example, rewarding the agent whenever its selections improve the performance on the primary task. We also explore learning per-example weights for the auxiliary loss. On CIFAR-100 grouped into 20 superclasses, our RL method outperforms human-labeled auxiliary tasks and matches the performance of a prominent bi-level optimization baseline. We present similarly strong results on other classification datasets. These results suggest RL is a viable path to generating effective auxiliary tasks.

Related papers

• Enhancing Training Data Attribution with Representational Optimization [57.61977909113113]
  Training data attribution methods aim to measure how training data impacts a model's predictions.<n>We propose AirRep, a representation-based approach that closes this gap by learning task-specific and model-aligned representations explicitly for TDA.<n>AirRep introduces two key innovations: a trainable encoder tuned for attribution quality, and an attention-based pooling mechanism that enables accurate estimation of group-wise influence.
  arXiv  Detail & Related papers  (2025-05-24T05:17:53Z)
• Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning [1.2952597101899859]
  We study task selection to enhance sample efficiency in model-agnostic meta-reinforcement learning (MAML-RL)<n>We propose a coreset-based task selection approach that selects a weighted subset of tasks based on how diverse they are in gradient space.<n>We numerically validate this trend across multiple RL benchmark problems, illustrating the benefits of task selection beyond the LQR baseline.
  arXiv  Detail & Related papers  (2025-02-04T14:09:00Z)
• Reinforcement Learning via Auxiliary Task Distillation [24.87090247662755]
  We present Reinforcement Learning via Auxiliary Task Distillation (AuxDistill) AuxDistill enables reinforcement learning to perform long-horizon robot control problems by distilling behaviors from auxiliary tasks. We demonstrate that AuxDistill can learn a pixels-to-actions policy for a challenging multi-stage embodied object rearrangement task without demonstrations, a learning curriculum, or pre-trained skills.
  arXiv  Detail & Related papers  (2024-06-24T23:02:18Z)
• Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost [73.28626942658022]
  We aim at exploiting additional auxiliary labels from an independent (auxiliary) task to boost the primary task performance. Our method is architecture-based with a flexible asymmetric structure for the primary and auxiliary tasks. Experiments with six tasks on NYU v2, CityScapes, and Taskonomy datasets using VGG, ResNet, and ViT backbones validate the promising performance.
  arXiv  Detail & Related papers  (2024-05-09T11:50:19Z)
• ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL [80.10358123795946]
  We develop a framework for building multi-turn RL algorithms for fine-tuning large language models. Our framework adopts a hierarchical RL approach and runs two RL algorithms in parallel. Empirically, we find that ArCHer significantly improves efficiency and performance on agent tasks.
  arXiv  Detail & Related papers  (2024-02-29T18:45:56Z)
• Sample Efficient Reinforcement Learning by Automatically Learning to Compose Subtasks [3.1594865504808944]
  We propose an RL algorithm that automatically structure the reward function for sample efficiency, given a set of labels that signify subtasks. We evaluate our algorithm in a variety of sparse-reward environments.
  arXiv  Detail & Related papers  (2024-01-25T15:06:40Z)
• Learning to Optimize for Reinforcement Learning [58.01132862590378]
  Reinforcement learning (RL) is essentially different from supervised learning, and in practice, these learneds do not work well even in simple RL tasks. Agent-gradient distribution is non-independent and identically distributed, leading to inefficient meta-training. We show that, although only trained in toy tasks, our learned can generalize unseen complex tasks in Brax.
  arXiv  Detail & Related papers  (2023-02-03T00:11:02Z)
• Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data [100.33096338195723]
  We focus on Few-shot Learning with Auxiliary Data (FLAD) FLAD assumes access to auxiliary data during few-shot learning in hopes of improving generalization. We propose two algorithms -- EXP3-FLAD and UCB1-FLAD -- and compare them with prior FLAD methods that either explore or exploit.
  arXiv  Detail & Related papers  (2023-02-01T18:59:36Z)
• Composite Learning for Robust and Effective Dense Predictions [81.2055761433725]
  Multi-task learning promises better model generalization on a target task by jointly optimizing it with an auxiliary task. We find that jointly training a dense prediction (target) task with a self-supervised (auxiliary) task can consistently improve the performance of the target task, while eliminating the need for labeling auxiliary tasks.
  arXiv  Detail & Related papers  (2022-10-13T17:59:16Z)
• Reinforcement Learning with Automated Auxiliary Loss Search [34.83123677004838]
  We propose a principled and universal method for learning better representations with auxiliary loss functions. Specifically, we define a general auxiliary loss space of size $7.5 times 1020$ and explore the space with an efficient evolutionary search strategy. Empirical results show that the discovered auxiliary loss significantly improves the performance on both high-dimensional (image) and low-dimensional (vector) unseen tasks.
  arXiv  Detail & Related papers  (2022-10-12T09:24:53Z)
• DL-DRL: A double-level deep reinforcement learning approach for large-scale task scheduling of multi-UAV [65.07776277630228]
  We propose a double-level deep reinforcement learning (DL-DRL) approach based on a divide and conquer framework (DCF) Particularly, we design an encoder-decoder structured policy network in our upper-level DRL model to allocate the tasks to different UAVs. We also exploit another attention based policy network in our lower-level DRL model to construct the route for each UAV, with the objective to maximize the number of executed tasks.
  arXiv  Detail & Related papers  (2022-08-04T04:35:53Z)
• AANG: Automating Auxiliary Learning [110.36191309793135]
  We present an approach for automatically generating a suite of auxiliary objectives. We achieve this by deconstructing existing objectives within a novel unified taxonomy, identifying connections between them, and generating new ones based on the uncovered structure. This leads us to a principled and efficient algorithm for searching the space of generated objectives to find those most useful to a specified end-task.
  arXiv  Detail & Related papers  (2022-05-27T16:32:28Z)
• Lean Evolutionary Reinforcement Learning by Multitasking with Importance Sampling [20.9680985132322]
  We introduce a novel neuroevolutionary multitasking (NuEMT) algorithm to transfer information from a set of auxiliary tasks to the target (full length) RL task. We demonstrate that the NuEMT algorithm data-lean evolutionary RL, reducing expensive agent-environment interaction data requirements.
  arXiv  Detail & Related papers  (2022-03-21T10:06:16Z)
• Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation [87.1188556802942]
  We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. We propose a novel Cross-Task Relation Layer (CTRL), which encodes task dependencies between the semantic and depth predictions. Furthermore, we propose an Iterative Self-Learning (ISL) training scheme, which exploits semantic pseudo-labels to provide extra supervision on the target domain.
  arXiv  Detail & Related papers  (2021-05-17T13:42:09Z)
• Auxiliary Task Reweighting for Minimum-data Learning [118.69683270159108]
  Supervised learning requires a large amount of training data, limiting its application where labeled data is scarce. To compensate for data scarcity, one possible method is to utilize auxiliary tasks to provide additional supervision for the main task. We propose a method to automatically reweight auxiliary tasks in order to reduce the data requirement on the main task.
  arXiv  Detail & Related papers  (2020-10-16T08:45:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.