On the Global Convergence of Policy Gradient in Average Reward Markov Decision Processes

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action spaces. Our analysis shows that the policy gradient iterates converge to the optimal policy at a sublinear rate of $O\left({\frac{1}{T}}\right),$ which translates to $O\left({\log(T)}\right)$ regret, where $T$ represents the number of iterations. Prior work on performance bounds for discounted reward MDPs cannot be extended to average reward MDPs because the bounds grow proportional to the fifth power of the effective horizon. Thus, our primary contribution is in proving that the policy gradient algorithm converges for average-reward MDPs and in obtaining finite-time performance guarantees. In contrast to the existing discounted reward performance bounds, our performance bounds have an explicit dependence on constants that capture the complexity of the underlying MDP. Motivated by this observation, we reexamine and improve the existing performance bounds for discounted reward MDPs. We also present simulations to empirically evaluate the performance of average reward policy gradient algorithm.

Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization

In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set. By targeting maximal return under the most adversarial model from that set, RMDPs address performance sensitivity to misspecified environments. Yet, to preserve computational tractability, the uncertainty set is traditionally independently structured for each state. This so-called rectangularity condition is solely motivated by computational concerns. As a result, it lacks a practical incentive and may lead to overly conservative behavior. In this work, we study coupled reward RMDPs where the transition kernel is fixed, but the reward function lies within an $\alpha$-radius from a nominal one. We draw a direct connection between this type of non-rectangular reward-RMDPs and applying policy visitation frequency regularization. We introduce a policy-gradient method, and prove its convergence. Numerical experiments illustrate the learned policy's robustness and its less conservative behavior when compared to rectangular uncertainty.

Robust Reinforcement Learning via Adversarial Kernel Approximation

Robust Markov Decision Processes (RMDPs) provide a framework for sequential decision-making that is robust to perturbations on the transition kernel. However, robust reinforcement learning (RL) approaches in RMDPs do not scale well to realistic online settings with high-dimensional domains. By characterizing the adversarial kernel in RMDPs, we propose a novel approach for online robust RL that approximates the adversarial kernel and uses a standard (non-robust) RL algorithm to learn a robust policy. Notably, our approach can be applied on top of any underlying RL algorithm, enabling easy scaling to high-dimensional domains. Experiments in classic control tasks, MinAtar and DeepMind Control Suite demonstrate the effectiveness and the applicability of our method.

An Efficient Solution to s-Rectangular Robust Markov Decision Processes

We present an efficient robust value iteration for \texttt{s}-rectangular robust Markov Decision Processes (MDPs) with a time complexity comparable to standard (non-robust) MDPs which is significantly faster than any existing method. We do so by deriving the optimal robust Bellman operator in concrete forms using our $L_p$ water filling lemma. We unveil the exact form of the optimal policies, which turn out to be novel threshold policies with the probability of playing an action proportional to its advantage.

Policy Gradient for s-Rectangular Robust Markov Decision Processes

We present a novel robust policy gradient method (RPG) for s-rectangular robust Markov Decision Processes (MDPs). We are the first to derive the adversarial kernel in a closed form and demonstrate that it is a one-rank perturbation of the nominal kernel. This allows us to derive an RPG that is similar to the one used in non-robust MDPs, except with a robust Q-value function and an additional correction term. Both robust Q-values and correction terms are efficiently computable, thus the time complexity of our method matches that of non-robust MDPs, which is significantly faster compared to existing black box methods.

Policy Gradient for Reinforcement Learning with General Utilities

In Reinforcement Learning (RL), the goal of agents is to discover an optimal policy that maximizes the expected cumulative rewards. This objective may also be viewed as finding a policy that optimizes a linear function of its state-action occupancy measure, hereafter referred as Linear RL. However, many supervised and unsupervised RL problems are not covered in the Linear RL framework, such as apprenticeship learning, pure exploration and variational intrinsic control, where the objectives are non-linear functions of the occupancy measures. RL with non-linear utilities looks unwieldy, as methods like Bellman equation, value iteration, policy gradient, dynamic programming that had tremendous success in Linear RL, fail to trivially generalize. In this paper, we derive the policy gradient theorem for RL with general utilities. The policy gradient theorem proves to be a cornerstone in Linear RL due to its elegance and ease of implementability. Our policy gradient theorem for RL with general utilities shares the same elegance and ease of implementability. Based on the policy gradient theorem derived, we also present a simple sample-based algorithm. We believe our results will be of interest to the community and offer inspiration to future works in this generalized setting.

Efficient Policy Iteration for Robust Markov Decision Processes via Regularization

Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Recent work established the equivalence between \texttt{s} rectangular $L_p$ robust MDPs and regularized MDPs, and derived a regularized policy iteration scheme that enjoys the same level of efficiency as standard MDPs. However, there lacks a clear understanding of the policy improvement step. For example, we know the greedy policy can be stochastic but have little clue how each action affects this greedy policy. In this work, we focus on the policy improvement step and derive concrete forms for the greedy policy and the optimal robust Bellman operators. We find that the greedy policy is closely related to some combination of the top $k$ actions, which provides a novel characterization of its stochasticity. The exact nature of the combination depends on the shape of the uncertainty set. Furthermore, our results allow us to efficiently compute the policy improvement step by a simple binary search, without turning to an external optimization subroutine. Moreover, for $L_1, L_2$, and $L_\infty$ robust MDPs, we can even get rid of the binary search and evaluate the optimal robust Bellman operators exactly. Our work greatly extends existing results on solving \texttt{s}-rectangular $L_p$ robust MDPs via regularized policy iteration and can be readily adapted to sample-based model-free algorithms.

The Geometry of Robust Value Functions

The space of value functions is a fundamental concept in reinforcement learning. Characterizing its geometric properties may provide insights for optimization and representation. Existing works mainly focus on the value space for Markov Decision Processes (MDPs). In this paper, we study the geometry of the robust value space for the more general Robust MDPs (RMDPs) setting, where transition uncertainties are considered. Specifically, since we find it hard to directly adapt prior approaches to RMDPs, we start with revisiting the non-robust case, and introduce a new perspective that enables us to characterize both the non-robust and robust value space in a similar fashion. The key of this perspective is to decompose the value space, in a state-wise manner, into unions of hypersurfaces. Through our analysis, we show that the robust value space is determined by a set of conic hypersurfaces, each of which contains the robust values of all policies that agree on one state. Furthermore, we find that taking only extreme points in the uncertainty set is sufficient to determine the robust value space. Finally, we discuss some other aspects about the robust value space, including its non-convexity and policy agreement on multiple states.