Searcharxiv⌕ Search

arXiv subjects

Ankur Naskar

Publications and source records attributed to Ankur Naskar.

9 recordsLinked to original sources

Federated TD Learning in Heterogeneous Environments with Average Rewards: A Two-timescale Approach with Polyak-Ruppert Averaging

Federated Reinforcement Learning (FRL) provides a promising way to speedup training in reinforcement learning when one has access to multiple edge devices that can operate in parallel. Recently, it has been shown that even when these edge devices have access to different dynamic models---such as cars or robots with differing system configurations---an optimal convergence rate that has a linear speedup proportional to the number of devices is achievable. However, this result requires that the algorithm's stepsize be chosen in a manner that depends on the unknown model parameters. Also, it applies only to a discounted setting, which has been argued to fit episodic tasks better than continuing control tasks. In this paper, we obtain finite-time bounds for heterogeneous FRL with average rewards. We show that optimal convergence rate and linear speedup are achievable even with a universal stepsize choice, independent of the underlying dynamics. To achieve our result, we modify the existing one-timescale FRL method to a novel two-timescale variant that additionally incorporates iterate averaging. We remark that this idea also extends to other settings already studied in the literature, such as the homogeneous FRL or the heterogeneous case with a discounted cost function.

cs.LG↗

Sample-Efficient Reinforcement Learning with General Utilities via Neural Dual Critics

Reinforcement learning with general utilities optimizes nonlinear functionals of policy-induced occupancy measures. We develop a natural actor-critic method for concave RLGU objectives using an exact variational dual representation, whose existence follows from concavity and differentiability, with explicit constructions for a broad class of separable occupancy utilities. Rather than estimating the occupancy measure and then forming the policy-gradient pseudo-reward, our method learns this pseudo-reward directly as a function of the state-action pair using a neural critic. The critic is trained by projected stochastic updates, while multilevel Monte Carlo combines outputs across training horizons to control its bias at logarithmic expected cost. Our analysis separates conditional actor bias from estimator second moments and accounts explicitly for dual optimization, critic approximation, and neural linearization errors. Under policy-transfer, dual-stability, and local critic-regularity conditions, the method achieves $\widetilde{O}(T^{-1/2})$ global convergence above policy, critic-class, and finite-width approximation errors using $\widetilde{O}(T)$ expected environment transitions and reference samples. For a fixed critic representation, this yields $\widetilde{O}(ε^{-2})$ sampling complexity above the approximation floor, covering infinite state-action spaces and occupancy utilities beyond fixed finite vectors of returns.

cs.LG↗

Hierarchical Multilevel Monte Carlo for Order-Optimal Neural Actor-Critic in Average-Reward CMDPs

Constrained Markov Decision Processes (CMDPs) provide a natural framework for reinforcement learning in safety-critical applications, where agents maximize long-term reward while satisfying long-term constraints. Although primal-dual actor-critic methods with linear critics are well understood, extending order-optimal convergence guarantees to neural critics in average-reward CMDPs has remained open. The main challenge is a fundamental bias-cost trade-off in neural critic estimation: under Neural Tangent Kernel (NTK) analysis, reducing critic bias substantially increases critic optimization cost, preventing order-optimal convergence in the primal-dual framework. We resolve this bottleneck by introducing a hierarchical Multilevel Monte Carlo (MLMC) neural critic that performs debiasing simultaneously across trajectory sampling and critic optimization. The resulting estimator attains the bias of a long critic optimization run with only logarithmic expected sample cost. Building on this estimator, we develop a primal-dual Natural Actor-Critic algorithm that achieves both an optimality gap and a constraint violation of order $\tilde{O}(T^{-1/2})$. This establishes the first order-optimal convergence guarantees for infinite-horizon average-reward CMDPs with general policy parameterization and neural critics, while eliminating the need to know the underlying mixing time. Our results are novel even in the unconstrained setting.

cs.LG↗

Finite-Time Analysis of Discounted Exponential-Utility Reinforcement Learning

Discounted exponential utility provides a principled criterion for risk-sensitive sequential decision-making, but its nonlinear structure complicates reinforcement learning. A recent work \citep{thoppe2026reinforcement} addressed this difficulty by introducing a Bellman-compatible surrogate and two model-free fixed-point algorithms for optimizing it over stationary policies. However, their main convergence results are asymptotic. In this work, we establish finite-time rates of $\tilde{O} (1/\sqrt{n})$ for the aforementioned two algorithms under asynchronous Markovian sampling, where $n$ is the iteration index and $\tilde{O}$ hides logarithmic expressions. Importantly, we employ parameter-free choices for the stepsize parameter to derive these rate results. For the algorithmically simpler one-timescale method, the main challenge is that its update equation is not directly aligned with the contraction geometry of its underlying power-law operator. We overcome this mismatch by exploiting the boundedness, monotonicity, and homogeneity of the operator to obtain a local pseudo-contraction property for the relative-error dynamics. We then use a Moreau-envelope-based Lyapunov function and Polyak--Ruppert averaging to obtain the stated convergence rate with parameter-free stepsizes. For the two-timescale method, the main challenge is to control a tracking error on the faster timescale. These results provide the first finite-time guarantees for model-free discounted exponential-utility reinforcement learning.

cs.LG↗

Bias-Controlled Primal-Dual Natural Actor-Critic: Optimal Rates for Constrained Multi-Objective Average-Reward RL

Many reinforcement learning (RL) problems in the infinite-horizon average-reward setting require optimizing multiple conflicting objectives while satisfying multiple safety constraints. A common approach is concave scalarization, where the agent maximizes a utility $ f(J^π_{r_1}, \ldots, J^π_{r_M}) $ subject to a scalarized constraint $ g(J^π_{c_1}, \ldots, J^π_{c_N}) \ge 0 $, where $J^π_{r_m}$ and $J^π_{c_n}$ denote the average-reward and cost under policy $π$. However, the nonlinearity of $f$ and $g$ introduces bias in policy-gradient and actor-critic methods, since gradients must be evaluated using noisy estimates of $J^π,$ and $ \mathbb{E}[\partial f(J^π)] \neq \partial f(\mathbb{E}[J^π]),$ and this bias propagates through both primal and dual updates. We propose an MLMC-based primal-dual Natural Actor-Critic algorithm for average-reward MDPs that controls bias in scalarized objectives, constraint evaluation, and actor-critic estimation without requiring mixing-time knowledge. We show that the algorithm achieves optimal global convergence and constraint-violation rates of $ \tilde{O}(1/\sqrt{T}) $. To our knowledge, this is the first result establishing optimal convergence for concave scalarized multi-objective RL in the average-reward setting, both with and without constraints, and the first to do so without mixing-time information even in the absence of scalarization.

cs.LG↗

Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs

Reinforcement learning (RL) for exponential-utility optimization in discounted Markov decision processes (MDPs) lacks principled value-based algorithms. We address this gap in the fixed risk-aversion setting. Building on the Bellman-type equation for exponential utility studied in \cite{porteus1975optimality}, we derive two Q-value-style extensions and show that the associated operators are contractions in the $L_\infty$ and sup-log/Thompson metrics, respectively. We characterize their fixed points and prove that the induced greedy stationary policy is optimal for the exponential-utility objective among stationary policies. These structural results lead to two model-free algorithms: a two-timescale Q-learning--style algorithm, for which we establish almost-sure convergence and provide finite-time convergence rates via timescale separation, and a one-timescale algorithm governed by a sublinear power-law operator. Since the latter does not admit a global contraction in standard metrics, we prove its convergence using delicate arguments based on local Lipschitzness, monotonicity, homogeneity, and Dini derivatives, and provide a scalar finite-time analysis that highlights the challenges in obtaining convergence rates in the vector case. Our work provides a foundation for value-based RL under exponential-utility objectives.

cs.LG↗

Parameter-free Optimal Rates for Nonlinear Semi-Norm Contractions with Applications to $Q$-Learning

Algorithms for solving \textit{nonlinear} fixed-point equations -- such as average-reward \textit{$Q$-learning} and \textit{TD-learning} -- often involve semi-norm contractions. Achieving parameter-free optimal convergence rates for these methods via Polyak--Ruppert averaging has remained elusive, largely due to the non-monotonicity of such semi-norms. We close this gap by (i.) recasting the averaged error as a linear recursion involving a nonlinear perturbation, and (ii.) taming the nonlinearity by coupling the semi-norm's contraction with the monotonicity of a suitably induced norm. Our main result yields the first parameter-free $\tilde{O}(1/\sqrt{t})$ optimal rates for $Q$-learning in both average-reward and exponentially discounted settings, where $t$ denotes the iteration index. The result applies within a broad framework that accommodates synchronous and asynchronous updates, single-agent and distributed deployments, and data streams obtained either from simulators or along Markovian trajectories.

cs.LG↗

Parameter-Free Federated TD Learning with Markov Noise in Heterogeneous Environments

Federated learning (FL) can dramatically speed up reinforcement learning by distributing exploration and training across multiple agents. It can guarantee an optimal convergence rate that scales linearly in the number of agents, i.e., a rate of $\tilde{O}(1/(NT)),$ where $T$ is the iteration index and $N$ is the number of agents. However, when the training samples arise from a Markov chain, existing results on TD learning achieving this rate require the algorithm to depend on unknown problem parameters. We close this gap by proposing a two-timescale Federated Temporal Difference (FTD) learning with Polyak-Ruppert averaging. Our method provably attains the optimal $\tilde{O}(1/NT)$ rate in both average-reward and discounted settings--offering a parameter-free FTD approach for Markovian data. Although our results are novel even in the single-agent setting, they apply to the more realistic and challenging scenario of FL with heterogeneous environments.

cs.LG↗

Weakening Total Coloring Conjecture: Weak TCC and Hadwiger's Conjecture on Total Graphs

Hadwiger's conjecture is one of the most important and long-standing conjectures in graph theory. Reed and Seymour showed in 2004 that Hadwiger's conjecture is true for line graphs. We investigate this conjecture on the closely related class of total graphs. The total graph of $G$, denoted by $T(G)$, is defined on the vertex set $V(G)\sqcup E(G)$ with $c_1,c_2\in V(G)\sqcup E(G)$ adjacent whenever $c_1$ and $c_2$ are adjacent to or incident on each other in $G$. We first show that there exists a constant $C$ such that, if the connectivity of $G$ is at least $C$, then Hadwiger's conjecture is true for $T(G)$. The total chromatic number $χ"(G)$ of a graph $G$ is defined to be equal to the chromatic number of its total graph. That is, $χ"(G)=χ(T(G))$. Another well-known conjecture in graph theory, the total coloring conjecture or TCC, states that for every graph $G$, $χ"(G)\leqΔ(G)+2$, where $Δ(G)$ is the maximum degree of $G$. We show that if a weaker version of the total coloring conjecture (weak TCC) namely, $χ"(G)\leqΔ(G)+3$, is true for a class of graphs $\mathcal{F}$ that is closed under the operation of taking subgraphs, then Hadwiger's conjecture is true for the class of total graphs of graphs in $\mathcal{F}$. This motivated us to look for classes of graphs that satisfy weak TCC. It may be noted that a complete proof of TCC for even 4-colorable graphs (in fact even for planar graphs) has remained elusive even after decades of effort; but weak TCC can be proved easily for 4-colorable graphs. We noticed that in spite of the interest in studying $χ"(G)$ in terms of $χ(G)$ right from the initial days, weak TCC is not proven to be true for $k$-colorable graphs even for $k=5$. In the second half of the paper, we make a contribution to the literature on total coloring by proving that $χ"(G)\leqΔ(G)+3$ for every 5-colorable graph $G$.

math.CO↗