English

Improving Stochastic Action-Constrained Reinforcement Learning via Truncated Distributions

Machine Learning 2025-12-01 v1 Systems and Control Systems and Control

Abstract

In reinforcement learning (RL), it is often advantageous to consider additional constraints on the action space to ensure safety or action relevance. Existing work on such action-constrained RL faces challenges regarding effective policy updates, computational efficiency, and predictable runtime. Recent work proposes to use truncated normal distributions for stochastic policy gradient methods. However, the computation of key characteristics, such as the entropy, log-probability, and their gradients, becomes intractable under complex constraints. Hence, prior work approximates these using the non-truncated distributions, which severely degrades performance. We argue that accurate estimation of these characteristics is crucial in the action-constrained RL setting, and propose efficient numerical approximations for them. We also provide an efficient sampling strategy for truncated policy distributions and validate our approach on three benchmark environments, which demonstrate significant performance improvements when using accurate estimations.

Keywords

Cite

@article{arxiv.2511.22406,
  title  = {Improving Stochastic Action-Constrained Reinforcement Learning via Truncated Distributions},
  author = {Roland Stolz and Michael Eichelbeck and Matthias Althoff},
  journal= {arXiv preprint arXiv:2511.22406},
  year   = {2025}
}

Comments

Accepted at the AAAI26 conference main technical track

R2 v1 2026-07-01T07:57:58.906Z