mlsanityData to 14 Oct 2026

Steady-State Error Compensation for Reinforcement Learning with Quadratic Rewards

arXiv 2402.09075 ↗First posted 14 Feb 2024eess.SY cs.LG cs.SYcited by 0

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

The selection of a reward function in Reinforcement Learning (RL) has garnered significant attention because of its impact on system performance. Issues of significant steady-state errors often manifest when quadratic reward functions are employed. Although absolute-value-type reward functions alleviate this problem, they tend to induce substantial fluctuations in specific system states, leading to abrupt changes. In response to this challenge, this study proposes an approach that introduces an integral term. By integrating this integral term into quadratic-type reward functions, the RL algorithm is adeptly tuned, augmenting the system's consideration of reward history, and consequently alleviates concerns related to steady-state errors. Through experiments and performance evaluations on the Adaptive Cruise Control (ACC) and lane change models, we validate that the proposed method effectively diminishes steady-state errors and does not cause significant spikes in some system states.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 6 of its 19 references that are in the map. First posted on arXiv 14 Feb 2024.

Builds on

6 of 19 references.

References · 6

  1. 2015Continuous control with deep reinforcement learningcited by 3,407
  2. 2017Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learningcited by 950
  3. 2017Deep Reinforcement Learning: An Overviewcited by 333
  4. 2018An Introduction to Deep Reinforcement Learningcited by 206
  5. 2019Comparison of Deep Reinforcement Learning and Model Predictive Control for Adaptive Cruise Controlcited by 22
  6. 2020Numerically Stable Dynamic Bicycle Model for Discrete-time Controlcited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
  2. 2026When Errors Can Be Beneficial: A Categorization of Imperfect Rewards for Policy Gradient
  3. 2025Learning a Pessimistic Reward Model in RLHF
  4. 2026Verifier Errors in RLVR: Reward Hacking, Limits of Feedback, and Selective Control
  5. 2024Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
  6. 2018Learning the Reward Function for a Misspecified Model
  7. 2025Reducing Reward Dependence in RL Through Adaptive Confidence Discounting
  8. 2024Adaptive Reward Design for Reinforcement Learning