The paper analyzes the sample complexities for policy evaluation with linear function approximation.
problem Policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
method Investigates sample complexities for two policy evaluation algorithms: TD and TDC.
result Establishes high-probability sample complexity bounds for policy evaluation algorithms.
The paper analyzes an actor-critic algorithm with target networks for deep reinforcement learning.
problem Lack of theoretical understanding of target networks in actor-critic methods.
method Proposes a theoretical analysis of an online target-based actor-critic algorithm with linear function approximation.
result Establishes asymptotic convergence results and finite-time analysis for both critic and actor.
This work analyzes how neural networks learn representations in actor-critic algorithms.
problem Theoretical support for neural AC algorithms is limited to linear function approximations.
method Mean-field analysis of a two-timescale learning AC algorithm with overparameterized networks.
result Neural AC finds the globally optimal policy at a sublinear rate in the continuous-time and infinite-width limiting regime.
Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.
problem Analyzing Greedy-GQ for reinforcement learning with Markovian noise.
method Develops finite-sample analysis for Greedy-GQ with linear function approximation under Markovian noise.
result Provides theoretical justification for choosing stepsizes for faster convergence.
This paper analyzes the sample complexity of two timescale reinforcement learning algorithms.
problem Analyzing the sample complexity of two timescale reinforcement learning algorithms.
method Non-asymptotic analysis of linear and nonlinear TDC and Greedy-GQ algorithms under Markovian sampling with constant stepsize.
result The paper provides non-asymptotic convergence results for two timescale linear and nonlinear TDC and Greedy-GQ algorithms.
Paper analyzes normal approximation for two-timescale stochastic algorithms, revealing interaction between fast and slow timescales.
problem Non-asymptotic bounds for accuracy of normal approximation in linear two-timescale stochastic approximation algorithms.
method Established bounds for normal approximation in terms of convex distance, focusing on last iterate and Polyak-Ruppert averaging.
result Normal approximation rate for the last iterate improves with increased timescale separation, while it decreases in the averaged setting.
This study improves convergence of two-timescale SA under Markovian noise in reinforcement learning.
problem Stability and convergence of two-timescale stochastic approximations under Markovian noise.
method Introduced a new control strategy for the fast timescale parameter.
result Established almost sure convergence of TDC with eligibility traces under off-policy learning with linear function approximation.
Paper analyzes finite-time performance of SA in RL with Markovian noise.
problem Finite-time analysis of linear two-timescale stochastic approximation with Markovian noise.
method Finite-time analysis of linear two-timescale SA with Markovian noise, considering both transient and steady-state terms.
result No discrepancy in convergence rate between Markovian and martingale noise; transient term is o ( 1 / k c ) o(1/k^c) o ( 1/ k c ) and steady-state term is O ( 1 / k ) {\cal O}(1/k) O ( 1/ k ) . COF-PAC converges with novel critic and learning method.
problem Convergent off-policy actor-critic with function approximation.
method Two-timescale approach with Gradient Emphasis Learning (GEM).
result First provably convergent COF-PAC with linear critics and nonlinear actor.
Two single-timescale algorithms improve TD learning with nonlinear approximations.
problem Optimizing TD learning with nonlinear smooth function approximation.
method Proposes two single-timescale single-loop algorithms with momentum and variance reduction.
result Achieves O ( ε − 4 ) O(\varepsilon^{-4}) O ( ε − 4 ) sample complexity for the first algorithm and O ( ε − 3 ) O(\varepsilon^{-3}) O ( ε − 3 ) for the second. Introduces TDRC to balance TD's ease and soundness.
problem TD learning's instability and divergence issues.
method Gradient Temporal-Difference Learning with Regularized Corrections (TDRC).
result TDRC performs as well as TD when TD works, but is sound in divergent cases.
Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.
problem Learning dynamics in zero-sum polymatrix games under different information settings.
method Two-timescale learning dynamics combining smoothed best-response updates and TD-learning for estimating local payoff functions.
result Polynomial-time finite-sample guarantees for convergence to an ε-Nash equilibrium in the minimal information case.
Study on distributional TD learning with linear approximations for better return estimation.
problem Estimating the return distribution of a policy in reinforcement learning.
method Finite-sample analysis of distributional TD learning with linear function approximation, using the linear-categorical Bellman equation and exponential stability arguments for products of random matrices.
result Sample complexity of linear distributional TD learning matches that of classic linear TD learning, indicating similar difficulty in estimating return distribution versus its expectation.
Improved TD(0) algorithm for reinforcement learning with linear approximations.
problem Sensitivity of TD(0) to stepsizes and slow convergence.
method AdaTD(0) - Adaptive projected variant of TD(0) with linear function approximation.
result AdaTD(0) converges faster and is less sensitive to stepsizes.
PFedRL-Rep learns shared and personalized policies for heterogeneous environments.
problem Poor performance of single policy in heterogeneous environments.
method Develops PFedRL-Rep framework with shared feature representation and personalized weights.
result Proves linear convergence speedup with respect to the number of agents.
New algorithms improve distributional TD learning with linear approximations.
problem Estimating return distributions in reinforcement learning.
method Fine-grained analysis of linear-categorical Bellman equation, variance reduction techniques.
result Tight sample complexity bounds for distributional TD learning with linear approximations.
Stochastic differential equation approximation for linear TD(0) under Markovian noise
problem Temporal-difference learning with linear function approximation
method Stochastic differential equation approximation
result Explains the constant-stepsize error floor
In this paper we present a framework to analyze the asymptotic behavior of two timescale stochastic approximation algorithms including those with set-valued mean fields. This paper builds on the works of Borkar and Perkins & Leslie. The framework presented herein is more general as compared to the synchronous two times…
Improved TD learning with tail averaging and regularization achieves optimal convergence rates.
problem Convergence analysis of TD learning with linear function approximation.
method Tail-averaging and regularization applied to TD learning algorithm.
result Achieves optimal O ( 1 / t ) O(1/t) O ( 1/ t ) convergence rate in expectation and with high probability. In this paper, we provide a unified analysis of temporal difference learning algorithms with linear function approximators by exploiting their connections to Markov jump linear systems (MJLS). We tailor the MJLS theory developed in the control community to characterize the exact behaviors of the first and second order …
The family of temporal difference (TD) methods span a spectrum from computationally frugal linear methods like TD(λ) to data efficient least squares methods. Least square methods make the best use of available data directly computing the TD solution and thus do not require tuning a typically highly sensitive learning r…
Proposes a convergent TD algorithm for off-policy RL.
problem Learning value function from different policies in RL.
method Convergent on-policy TD algorithm with linear function approximation.
result Proposes a convergent TD algorithm for off-policy RL.
Paper improves TD(0) convergence rate with LFA, i.i.d. samples, and averaging.
problem Improving convergence rate of TD(0) with linear function approximation.
method Polyak-Juditsky averaging, i.i.d. samples, strong mixing assumption.
result Established a new convergence rate for Mean-Square Error (MSE) of approximated function.
Proves convergence of neural networks in a two-timescale regime.
problem Training dynamics of shallow neural networks.
method Two-timescale regime analysis of gradient flow.
result Gradient flow converges to global optimum in non-convex optimization.
Uniform TD(0) bound derived for function approximation with Markov noise.
problem Uniform concentration bound for TD(0) with function approximation.
method Contractive stochastic approximation, martingale and Markov noises, Poisson equation, relaxed concentration inequalities.
result Uniform all-time concentration bound for TD(0) with linear function approximation.
Paper analyzes TD( λ λ λ ) convergence rates for arbitrary features.
problem Convergence rates for linear TD( λ λ λ ) under arbitrary features. method Developed a novel stochastic approximation result for arbitrary features.
result Established L 2 L^2 L 2 convergence rates for linear TD( λ λ λ ) without linearly independent features assumption. The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal difference (TD) learning algorithms and provide theoretical analysis on their conver…
Paper shows TD learning without projection converges robustly.
problem Investigate convergence of TD learning with linear approx.
method Simple unprojected TD(0) with novel self-bounding property.
result TD(0) converges with rate O ~ ( 1 / T ) \widetilde{\mathcal{O}}(1/\sqrt{T}) O ( 1/ T ) . The true online TD(λ) algorithm has recently been proposed (van Seijen and Sutton, 2014) as a universal replacement for the popular TD(λ) algorithm, in temporal-difference learning and reinforcement learning. True online TD(λ) has better theoretical properties than conventional TD(λ), and the expectation is that it als…
While there are convergence guarantees for temporal difference (TD) learning when using linear function approximators, the situation for nonlinear models is far less understood, and divergent examples are known. Here we take a first step towards extending theoretical convergence guarantees to TD learning with nonlinear…
Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new policy-evaluation algorithms that fill a longstanding algorithmic void in reinforcem…
Study Whittle index learning algorithms for restless bandits with constant stepsizes.
problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.
Our understanding of reinforcement learning (RL) has been shaped by theoretical and empirical results that were obtained decades ago using tabular representations and linear function approximators. These results suggest that RL methods that use temporal differencing (TD) are superior to direct Monte Carlo estimation (M…
Paper improves TD learning algorithm bounds with linear approx.
problem Sharp bounds for TD method performance in MDPs.
method Polyak-Ruppert averaging, universal step size, refined error bounds, stability of random matrices.
result Near-optimal variance and bias terms achieved.
We provide non-asymptotic bounds for the well-known temporal difference learning algorithm TD(0) with linear function approximators. These include high-probability bounds as well as bounds in expectation. Our analysis suggests that a step-size inversely proportional to the number of iterations cannot guarantee optimal …
Temporal difference learning (TD) is a simple iterative algorithm used to estimate the value function corresponding to a given policy in a Markov decision process. Although TD is one of the most widely used algorithms in reinforcement learning, its theoretical analysis has proved challenging and few guarantees on its s…
Improved TD learning reduces variance and bias errors.
problem Inefficient optimization variance in TD learning.
method Proposed a mathematically solid analysis of VRTD, showing linear convergence rate and reduced variance and bias errors.
result VRTD converges to a fixed-point solution with reduced variance and bias errors compared to vanilla TD.
TD(0) with Polyak-Ruppert averaging achieves robust and fast convergence rates
problem TD(0) learning under Markovian sampling
method Polyak-Ruppert averaging with a single stepsize
result Simultaneous high-probability convergence guarantees for TD(0) iterates and PR average
This paper formalizes Q Q Q -learning and linear TD convergence using Lean 4.
problem Formalizing convergence properties of Q Q Q -learning and linear TD learning. method Formal verification using Lean 4 theorem prover and Mathlib library.
result Formalized almost sure convergence of Q Q Q -learning and linear TD learning. Swift-Sarsa combines TD learning with Sarsa to control tasks robustly.
problem Learning effective control policies from noisy signals.
method Combines True Online Sarsa( λ λ λ ) with step-size optimization and decay. result Swift-Sarsa learns relevant signals without prior knowledge.
New bounds show linear predictors rarely overfit with certain optimization methods.
problem Bounding test error for linear predictors with stochastic optimization methods.
method Coupling argument for fixed point methods like stochastic and batch mirror descent.
result Locally-adapted rates that depend on predictor properties, not global problem structure.
Novel bounds improve TD learning consistency in RL.
problem Analyzing Temporal Difference learning's performance.
method High-dimensional concentration inequalities and Berry-Esseen bounds for Markov chain induced martingales.
result Sharp high-probability consistency guarantee for TD learning, matching asymptotic variance up to logarithmic factors.
Study on Adam-family methods for nonsmooth optimization with convergence guarantees.
problem Training nonsmooth neural networks with convergence guarantees.
method Two-timescale updating scheme and stochastic subgradient methods with gradient clipping.
result Convergence guarantees for various Adam-family methods in training nonsmooth neural networks.
Study analyzes a new algorithm for complex optimization problems.
problem Stochastic bilevel optimisation problems in continuous-time models.
method Continuous-time, two-timescale stochastic approximation algorithm.
result Obtained weak convergence rate using central limit theorem.
Study optimal and instance-dependent guarantees for solving linear equations with Markovian data.
problem Approximately solving linear fixed point equations with Markovian data.
method Non-asymptotic bounds and instance-dependent characterizations for stochastic approximation.
result Instance-optimality of the averaged SA estimator and matching upper and lower bounds.
RO-TD learns sparse value functions efficiently.
problem Learning sparse value functions efficiently.
method RO-TD integrates off-policy convergent gradient TD methods and online convex regularization.
result RO-TD learns sparse value functions with low computational complexity.
Improved TD learning reduces batch sampling error.
problem TD learning can be inaccurate in batch settings due to action weighting.
method Introduced PSEC-TD(0) to correct action weighting using importance sampling.
result PSEC-TD(0) produces more accurate value function estimates.
Study shows TD(0) with linear approx. converges for reversible Markov chains.
problem TD(0) divergence with off-policy and function approximation.
method Analyzes standard TD(0) with reversible Markov chains, adapting stochastic approximation framework.
result Establishes convergence with probability one for projected Bellman error = 0.