Generalization performance improvement of artificial intelligence deep reinforcement learning algorithms for large-scale high-dimensional decision making

Abstract In large-scale high-dimensional decision-making scenarios, the system needs to maintain the policy output under the expansion of state, the intensive combination of actions and the change of task distribution. To improve the generalization performance of deep reinforcement learning, a generalization enhancement method driven by state-action collaboration and task distribution training was proposed. Three types of tasks, industrial scheduling, resource allocation and continuous control, were set up in the experiment, and 18 groups of training tasks and 12 groups of unseen test tasks were constructed. The state dimension covered 128, 256 and 512 dimensions, and the action scale could reach ten thousand levels. The results show that the average reward of unseen tasks reaches 0.858, the success rate reaches 92.8%, the generalization gap is reduced to 11.6%, the constraint violation rate is reduced to 3.4%, and the inference delay is 24.1ms. Ablation experiments show that the success rate decreases by 5.6% points after removing state-action collaboration, and the generalization gap increases by 7.1% points after removing task distribution training. The results show that the proposed method improves the transfer generalization stability of the model in high-dimensional decision-making.

Authors

Publication Details

Journal
Discover Applied Sciences
Published
2026-11-14
DOI
https://doi.org/10.1007/s42452-026-09894-2
Primary Topic
Reinforcement Learning in Robotics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Generalization performance improvement of artificial intelligence deep reinforcement learning algorithms for large-scale high-dimensional decision making

Hanyu Zhang
Discover Applied Sciences
Reinforcement Learning in Robotics
article

Generalization performance improvement of artificial intelligence deep reinforcement learning algorithms for large-scale high-dimensional decision making

Hanyu Zhang
article en

Abstract

Abstract In large-scale high-dimensional decision-making scenarios, the system needs to maintain the policy output under the expansion of state, the intensive combination of actions and the change of task distribution. To improve the generalization performance of deep reinforcement learning, a generalization enhancement method driven by state-action collaboration and task distribution training was proposed. Three types of tasks, industrial scheduling, resource allocation and continuous control, were set up in the experiment, and 18 groups of training tasks and 12 groups of unseen test tasks were constructed. The state dimension covered 128, 256 and 512 dimensions, and the action scale could reach ten thousand levels. The results show that the average reward of unseen tasks reaches 0.858, the success rate reaches 92.8%, the generalization gap is reduced to 11.6%, the constraint violation rate is reduced to 3.4%, and the inference delay is 24.1ms. Ablation experiments show that the success rate decreases by 5.6% points after removing state-action collaboration, and the generalization gap increases by 7.1% points after removing task distribution training. The results show that the proposed method improves the transfer generalization stability of the model in high-dimensional decision-making.

Discover Applied Sciences
Reinforcement Learning in Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon