Task Adaptation of Reinforcement Learning-based NAS Agents through Transfer Learning
On the map: Deep reinforcement learning methods → Deep RL algorithms and representations
Abstract (arXiv)
Recently, a novel paradigm has been proposed for reinforcement learning-based NAS agents, that revolves around the incremental improvement of a given architecture. We assess the abilities of such reinforcement learning agents to transfer between different tasks. We perform our evaluation using the Trans-NASBench-101 benchmark, and consider the efficacy of the transferred agents, as well as how quickly they can be trained. We find that pretraining an agent on one task benefits the performance of the agent in another task in all but 1 task when considering final performance. We also show that the training procedure for an agent can be shortened significantly by pretraining it on another task. Our results indicate that these effects occur regardless of the source or target task, although they are more pronounced for some tasks than for others. Our results show that transfer learning can be an effective tool in mitigating the computational cost of the initial training procedure for reinforcement learning-based NAS agents.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 20 of its 31 references that are in the map. First posted on arXiv 2 Dec 2024.
Builds on
20 of 31 references.
References · 20
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
- 2018DARTS: Differentiable Architecture Searchcited by 1,798
- 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
- 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
- 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
- 2022Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasetscited by 629
- 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 344
- 2016Designing Neural Network Architectures using Reinforcement Learningcited by 279
- 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 265
8 more
- 2016What makes ImageNet good for transfer learning?cited by 192
- 2018Efficient Multi-objective Neural Architecture Search via Lamarckian Evolutioncited by 153
- 2017Time Limits in Reinforcement Learningcited by 79
- 2021TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Searchcited by 58
- 2021NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Taskscited by 32
- 2021Learning Versatile Neural Architectures by Propagating Network Codescited by 9
- 2022AIO-P: Expanding Neural Performance Predictors Beyond Image Classificationcited by 8
- 2024Robustifying and Boosting Training-Free Neural Architecture Searchcited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Generalized Adaptive Transfer Network: Enhancing Transfer Learning in Reinforcement Learning Across Domains
- 2025Learning Where, What and How to Transfer: A Multi-Role Reinforcement Learning Approach for Evolutionary Multitasking
- 2025Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning
- 2026Predictive Representations for Skill Transfer in Reinforcement Learning
- 2026SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution
- 2024Transfer Reinforcement Learning in Heterogeneous Action Spaces using Subgoal Mapping
- 2024Task and Domain Adaptive Reinforcement Learning for Robot Control
- 2022On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning