Last-Iterate Guarantees for Online Reinforcement Learning in Structured Constrained MDPs

We study policy optimization for infinite-horizon, discounted constrained Markov decision processes (CMDPs). While existing theoretical guarantees typically hold for the mixture policy, deploying such a policy is computationally and memory intensive. This leads to a practical mismatch where a single (last-iterate) policy must be deployed. Recent theoretical works have thus focused on proving last-iterate convergence, but are largely limited to the tabular setting or to algorithmic variants that are rarely used in practice. To address this, we use the classic inexact augmented Lagrangian ($\texttt{AL}$) method from constrained optimization, and propose a general framework with provable last-iterate convergence for CMDPs. We first focus on the tabular setting and propose to solve the $\texttt{AL}$ sub-problem with projected Q-ascent ($\texttt{PQA}$). Combining the theoretical guarantees of $\texttt{PQA}$ and the standard $\texttt{AL}$ analysis enables us to establish global last-iterate convergence. We generalize these results to handle log-linear policies, and demonstrate that an efficient, projected variant of $\texttt{PQA}$ can achieve last-iterate convergence with comparable guarantees as prior work. Finally, we demonstrate that our framework scales to complex non-linear policies, and evaluate it on continuous control tasks.

Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used to enforce safety constraints while optimizing performance. However, existing methods often suffer from significant safety violations or require a high sample complexity to generate near-optimal policies. We address two settings: relaxed feasibility, where small violations are allowed, and strict feasibility, where no violation is allowed. We propose a model-based primal-dual algorithm that balances regret and bounded constraint violations, drawing on techniques from online RL and constrained optimization. For relaxed feasibility, we prove that our algorithm returns an $\varepsilon$-optimal policy with $\varepsilon$-bounded violation with arbitrarily high probability, requiring $\tilde{O}\left(\frac{SAH^3}{\varepsilon^2}\right)$ learning episodes, matching the lower bound for unconstrained MDPs. For strict feasibility, we prove that our algorithm returns an $\varepsilon$-optimal policy with zero violation with arbitrarily high probability, requiring $\tilde{O}\left(\frac{SAH^5}{\varepsilon^2ζ^2}\right)$ learning episodes, where $ζ$ is the problem-dependent Slater constant characterizing the size of the feasible region. This result matches the lower bound for learning CMDPs with access to a generative model. Our results demonstrate that learning CMDPs in an online setting is as easy as learning with a generative model and is no more challenging than learning unconstrained MDPs when small violations are allowed.

We study online episodic Constrained Markov Decision Processes (CMDPs) under both stochastic and adversarial constraints. We provide a novel algorithm whose guarantees greatly improve those of the state-of-the-art best-of-both-worlds algorithm introduced by Stradi et al. (2025). In the stochastic regime, i.e., when the constraints are sampled from fixed but unknown distributions, our method achieves $\widetilde{\mathcal{O}}(\sqrt{T})$ regret and constraint violation without relying on Slater's condition, thereby handling settings where no strictly feasible solution exists. Moreover, we provide guarantees on the stronger notion of positive constraint violation, which does not allow to recover from large violation in the early episodes by playing strictly safe policies. In the adversarial regime, i.e., when the constraints may change arbitrarily between episodes, our algorithm ensures sublinear constraint violation without Slater's condition, and achieves sublinear $α$-regret with respect to the unconstrained optimum, where $α$ is a suitably defined multiplicative approximation factor. We further validate our results through synthetic experiments, showing the practical effectiveness of our algorithm.