mlsanityData to 14 Oct 2026

On Reward-Balancing Methods for Reinforcement Learning

arXiv 2604.20433 ↗First posted 22 Apr 2026math.OC cs.SY eess.SYcited by 0

On the map: Deep reinforcement learning methods → RL theory and sample complexity

Abstract (arXiv)

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform the RL problem into an equivalent one in which the optimal policies are greedy. For this procedure, referred to as normalization process, we provide a theoretical analysis of the involved transformations, emphasizing their algebraic structure. Then, we introduce a control-theoretic reformulation, recasting the reward-balancing procedure into an optimal control framework. The approach is further extended to address model uncertainty through stochastic model sampling, yielding normalization guarantees and probabilistic bounds on stochastic fluctuations. Using the proposed optimal control framework within a scenario model predictive control (MPC) setting, we demonstrate, through simulation studies, performance improvements over the current state-of-the-art.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods. Builds on 8 of its 16 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

8 of 16 references.

References · 8

  1. 2020MDP Homomorphic Networks: Group Symmetries in Reinforcement Learningcited by 142
  2. 2020Learning to Utilize Shaping Rewards: A New Approach of Reward Shapingcited by 114
  3. 2023The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyondcited by 36
  4. 2019Reward Shaping via Meta-Learningcited by 32
  5. 2013The Scenario Approach for Stochastic Model Predictive Control with Bounds on Closed-Loop Constraint Violationscited by 24
  6. 2019Data-driven distributionally robust LQR with multiplicative noisecited by 7
  7. 2024MDP Geometry, Normalization and Reward Balancing Solverscited by 3
  8. 2020Robust Control Design for Linear Systems via Multiplicative Noisecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Mathematical methods of reinforcement learning
  2. 2025Maximize Your Diffusion: A Study into Reward Maximization and Alignment for Diffusion-based Control
  3. 2025Recursive Reward Aggregation
  4. 2024Asynchronous Stochastic Approximation with Applications to Average-Reward Reinforcement Learning
  5. 2026UBP2: Uncertainty-Balanced Preference Planning for Efficient Preference-based Reinforcement Learning
  6. 2024On the Stochastic (Variance-Reduced) Proximal Gradient Method for Regularized Expected Reward Optimization
  7. 2026Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence
  8. 2020Average-reward model-free reinforcement learning: a systematic review and literature mapping