Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems
2025 · Oren Fivel, Matan Rudman, Kobi Cohen
Abstract
Deep reinforcement learning (DRL) has become a powerful tool for complex decision-making in machine learning and AI. However, traditional methods often assume perfect action execution, overlooking the uncertainties and deviations between an agent's selected actions and the actual system response. In real-world applications, such as robotics, mechatronics, and communication networks, execution mismatches arising from system dynamics, hardware constraints, and latency can significantly degrade performance. This work advances AI by developing a novel control-optimized DRL framework that explicitly models and compensates for action execution mismatches, a challenge largely overlooked in existing methods. Our approach establishes a structured two-stage process: determining the desired action and selecting the appropriate control signal to ensure proper execution. It trains the agent while accounting for action mismatches and controller corrections. By incorporating these factors into the tr
Authors
(none)
Tags
Stats
Related papers
- A Human Mixed Strategy Approach To Deep Reinforcement Learning (2018)7.50
- On The Mistaken Assumption Of Interchangeable Deep Reinforcement Learning Implementations (2025)0.00
- Deep Reinforcement Learning For Autonomous Cyber Defence: A Survey (2023)0.00
- Evaluating The Progress Of Deep Reinforcement Learning In The Real World: Aligning Domain-agnostic And Domain-specific Research (2021)0.00
- A3C-S: Automated Agent Accelerator Co-search Towards Efficient Deep Reinforcement Learning (2021)0.00
- Reducing The Deployment-time Inference Control Costs Of Deep Reinforcement Learning Agents Via An Asymmetric Architecture (2021)0.00
- Multi-fidelity Reinforcement Learning Control For Complex Dynamical Systems (2025)0.00
- Robust Deep Reinforcement Learning With Adaptive Adversarial Perturbations In Action Space (2024)6.20