We present two Policy Gradient-based algorithms with general parametrization in the context of infinite-horizon average reward Markov Decision Process (MDP). The first one employs Implicit Gradient Transport for variance reduction, ensuring an expected regret of the order $\tilde{\mathcal{O}}(T^{2/3})$. The second approach, rooted in Hessian-based techniques, ensures an expected regret of the order $\tilde{\mathcal{O}}(\sqrt{T})$. These results significantly improve the state-of-the-art $\tilde{\mathcal{O}}(T^{3/4})$ regret and achieve the theoretical lower bound. We also show that the average-reward function is approximately $L$-smooth, a result that was previously assumed in earlier works.

This work examines average-reward reinforcement learning with general policy parametrization. Existing state-of-the-art (SOTA) guarantees for this problem are either suboptimal or hindered by several challenges, including poor scalability with respect to the size of the state-action space, high iteration complexity, and a significant dependence on knowledge of mixing times and hitting times. To address these limitations, we propose a Multi-level Monte Carlo-based Natural Actor-Critic (MLMC-NAC) algorithm. Our work is the first to achieve a global convergence rate of $\tilde{\mathcal{O}}(1/\sqrt{T})$ for average-reward Markov Decision Processes (MDPs) (where $T$ is the horizon length), using an Actor-Critic approach. Moreover, the convergence rate does not scale with the size of the state space, therefore even being applicable to infinite state spaces.

Actor-Critic methods are widely used for their scalability, yet existing theoretical guarantees for infinite-horizon average-reward Markov Decision Processes (MDPs) often rely on restrictive ergodicity assumptions. We propose NAC-B, a Natural Actor-Critic with Batching, that achieves order-optimal regret of \$\tilde{O}(\sqrt{T})\$ in infinite-horizon average-reward MDPs under the unichain assumption, which permits both transient states and periodicity. This assumption is among the weakest under which the classic policy gradient theorem remains valid for average-reward settings. NAC-B employs function approximation for both the actor and the critic, enabling scalability to problems with large state and action spaces. The use of batching in our algorithm helps mitigate potential periodicity in the MDP and reduces stochasticity in gradient estimates, and our analysis formalizes these benefits through the introduction of the constants $C_{\text{hit}}$ and $C_{\text{tar}}$, which characterize the rate at which empirical averages over Markovian samples converge to the stationary distribution.

This paper investigates infinite-horizon average reward Constrained Markov Decision Processes (CMDPs) under general parametrized policies with smooth and bounded policy gradients. We propose a Primal-Dual Natural Actor-Critic algorithm that adeptly manages constraints while ensuring a high convergence rate. In particular, our algorithm achieves global convergence and constraint violation rates of $\tilde{\mathcal{O}}(1/\sqrt{T})$ over a horizon of length $T$ when the mixing time, $\tau_{\mathrm{mix}}$, is known to the learner. In absence of knowledge of $\tau_{\mathrm{mix}}$, the achievable rates change to $\tilde{\mathcal{O}}(1/T^{0.5-\epsilon})$ provided that $T \geq \tilde{\mathcal{O}}\left(\tau_{\mathrm{mix}}^{2/\epsilon}\right)$. Our results match the theoretical lower bound for Markov Decision Processes and establish a new benchmark in the theoretical exploration of average reward CMDPs.

This paper addresses the challenge of achieving order-optimal sample complexity in reinforcement learning for discounted Markov Decision Processes (MDPs) with general policy parameterization and multi-layer neural network critics. Existing approaches either fail to achieve the optimal rate or assume a linear critic. We introduce Natural Actor-Critic with Data Drop (NAC-DD) algorithm, which integrates Natural Policy Gradient methods with a Data Drop technique to mitigate statistical dependencies inherent in Markovian sampling. NAC-DD achieves an optimal sample complexity of $\tilde{\mathcal{O}}(1/\epsilon^2)$, marking a significant improvement over the previous state-of-the-art guarantee of $\tilde{O}(1/\epsilon^3)$. The algorithm employs a multi-layer neural network critic with differentiable activation functions, aligning with real-world applications where tabular policies and linear critics are insufficient. Our work represents the first to achieve order-optimal sample complexity for actor-critic methods with neural function approximation, continuous state and action spaces, and Markovian sampling. Empirical evaluations on benchmark tasks confirm the theoretical findings, demonstrating the practical efficacy of the proposed method.

Stochastic Heavy Ball (SHB) and Nesterov’s Accelerated Stochastic Gradient (ASG) are popular momentum methods in optimization. While the benefits of these acceleration ideas in deterministic settings are well understood, their advantages in stochastic optimization are unclear. Several works have recently claimed that SHB and ASG always help in stochastic optimization. Our work shows that i.) these claims are either flawed or one-sided (e.g., consider only the bias term but not the variance), and ii.) when both these terms are accounted for, SHB and ASG do not always help. Specifically, for any quadratic optimization, we obtain a lower bound on the sample complexity of SHB and ASG, accounting for both bias and variance, and show that the vanilla SGD can achieve the same bound.