Temporal-difference and Q-learning learn feature representations that converge to optimal ones.
problem Understanding how feature representations evolve in temporal-difference and Q-learning with neural networks.
method Mean-field theory applied to overparameterized two-layer neural networks.
result The feature representation converges to the optimal one, generalizing previous results.
Q-Learning overestimation bias influenced by learning rate, discount factor, and reward signal.
problem Overestimation bias in Q-Learning algorithm.
method Investigated the influence of learning rate, discount factor, and reward signal on Q-Learning's overestimation bias. Tuned parameters and used an exponential moving average of reward signal.
result Q-Learning can achieve more accurate value estimates by tuning parameters and using an exponential moving average of reward signal.
This paper formalizes Q-learning and linear TD convergence using Lean 4.
problem Formalizing convergence properties of Q-learning and linear TD learning. method Formal verification using Lean 4 theorem prover and Mathlib library.
result Formalized almost sure convergence of Q-learning and linear TD learning. Paper presents a new method for Bayesian deep learning that scales to Atari games.
problem Training neural networks on complex environments like Atari games is challenging.
method Adapted temporal difference Q-learning to work with Bayesian inference.
result TAGI allows for analytical inference of neural network parameters, achieving performance comparable to gradient-based methods.
We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that learns to estimate state-action values. We first test DQV's update rules…
Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to nonconvexity and even divergence in optimization. As a result, the global convergence …
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 develops bounds for stochastic approximation with averaging.
problem Establish high-probability bounds for averaged stochastic approximation.
method Develops a general framework for non-asymptotic concentration bounds.
result Derives sharp bounds for averaged iterates and tightens existing results.
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.
In the past few years, off-policy reinforcement learning methods have shown promising results in their application for robot control. Deep Q-learning, however, still suffers from poor data-efficiency and is susceptible to stochasticity in the environment or reward functions which is limiting with regard to real-world a…
In classical Q-learning, the objective is to maximize the sum of discounted rewards through iteratively using the Bellman equation as an update, in an attempt to estimate the action value function of the optimal policy. Conventionally, the loss function is defined as the temporal difference between the action value and…
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…
Accelerates TD learning for long-horizon reinforcement learning problems.
problem Slow convergence of conventional TD learning in long-horizon tasks.
method Introduces PID Accelerated Temporal Difference (PID TD) learning algorithms.
result Accelerates convergence of TD learning compared to conventional methods.
Unified analysis of stochastic iterative algorithms using Lyapunov functions.
problem Analyzing convergence of stochastic iterative algorithms for fixed-point equations.
method Lyapunov-based techniques for finite-time analysis of stochastic approximation algorithms.
result Unified mean-square convergence guarantees for various algorithms.
Study shows DQN's performance degrades with temporal dependence in data.
problem Temporal dependence in replayed data affects DQN's performance.
method Modelled τ-mixing data, derived risk bounds, and empirical validation. result Temporal dependence leads to a degradation in DQN's performance rate.
In this paper, we consider same-day delivery with vehicles and drones. Customers make delivery requests over the course of the day, and the dispatcher dynamically dispatches vehicles and drones to deliver the goods to customers before their delivery deadline. Vehicles can deliver multiple packages in one route but trav…
A new method stabilizes deep reinforcement learning by using QGraphs to retain replay memory information.
problem Stabilizing model-free off-policy deep reinforcement learning with soft divergence.
method Representing past experiences as a QGraph, selecting a subgraph with favorable structure, and using lower bounds for temporal difference learning.
result QG-DDPG method is less prone to soft divergence and more robust to hyperparameters.
New approach uses inverse reinforcement learning to improve language model training.
problem Training large language models using imitation learning methods.
method Developed a new method of inverse reinforcement learning to optimize sequences directly.
result IRL-based fine-tuning leads to better performance and diversity in language generation.
In this paper, the distributed edge caching problem in fog radio access networks (F-RANs) is investigated. By considering the unknown spatio-temporal content popularity and user preference, a user request model based on hidden Markov process is proposed to characterize the fluctuant spatio-temporal traffic demands in F…
QAM uses adjoint matching to optimize continuous-action RL policies efficiently.
problem Efficient optimization of expressive diffusion or flow-matching policies with respect to a Q-function.
method QAM leverages adjoint matching to bypass the numerical instability of backpropagation through multi-step denoising processes.
result QAM consistently outperforms prior approaches on hard, sparse reward tasks in offline and offline-to-online RL.
Temporal-difference (TD) learning is an important field in reinforcement learning. Sarsa and Q-Learning are among the most used TD algorithms. The Q(σ) algorithm (Sutton and Barto (2017)) unifies both. This paper extends the Q(σ) algorithm to an online multi-step algorithm Q(σ,λ) using eligibility traces and int…
We establish a new connection between value and policy based reinforcement learning (RL) based on a relationship between softmax temporal value consistency and policy optimality under entropy regularization. Specifically, we show that softmax consistent action values correspond to optimal entropy regularized policy pro…
This paper proposes a new algorithm for learning guidance rewards in RL.
problem Long-term temporal credit assignment in sparse or delayed reward environments.
method Surrogate RL objective with trajectory-space smoothing to learn guidance rewards.
result Guidance rewards can be learned without additional neural networks and have intuitive interpretation.
Motivated by the widespread use of temporal-difference (TD-) and Q-learning algorithms in reinforcement learning, this paper studies a class of biased stochastic approximation (SA) procedures under a mild "ergodic-like" assumption on the underlying stochastic noise sequence. Building upon a carefully designed multistep…
DO-IQS recovers optimal stopping region from expert trajectories, addressing specific challenges.
problem Recovering optimal stopping region from expert trajectories with unknown gain functions.
method Dynamics-Aware Offline Inverse Q-Learning incorporating temporal information and confidence-based oversampling.
result Demonstrated performance on real and artificial data, including optimal intervention for critical events.
Kernelized Q-learning achieves good performance with minimal data.
problem Efficient Q-learning in high-dimensional spaces.
method Kernelized Q-learning framework with effective dimensionality.
result Concrete regret bounds for linear and Gaussian RBF kernels.
Proposes a deep spectral Q-learning for mobile health data.
problem Personalized treatment assignment for patients with time-varying covariates.
method Integrates PCA with deep Q-learning for mixed frequency data.
result Mean return converges to optimal under estimated optimal policy.
The paper proposes a structure learning model for efficient reinforcement learning.
problem Efficient sample-based decision making in complex environments.
method Temporal Gaussian Mixture Model with structure learning.
result The model discovers the number of states and transition probabilities.
The breakthrough of deep Q-Learning on different types of environments revolutionized the algorithmic design of Reinforcement Learning to introduce more stable and robust algorithms, to that end many extensions to deep Q-Learning algorithm have been proposed to reduce the variance of the target values and the overestim…
The paper analyzes Q-learning in 2-player Markov games and provides gap-dependent logarithmic regret bounds.
problem Analyzing the cumulative regret of Nash Q-learning in 2-player turn-based stochastic Markov games.
method Proposed gap-dependent logarithmic upper bounds for cumulative regret in episodic tabular setting and discounted game setting.
result The proposed bounds match theoretical lower bounds up to a logarithmic term.
We present a new model-based reinforcement learning algorithm, Cooperative Prioritized Sweeping, for efficient learning in multi-agent Markov decision processes. The algorithm allows for sample-efficient learning on large problems by exploiting a factorization to approximate the value function. Our approach only requir…
New technique prevents Q-learning collapse by maximizing diversity among ensembles.
problem Value function collapse in ensemble Q-learning.
method Maximizing representation diversity through regularization.
result Regularized approach significantly outperforms existing methods.
This paper introduces sample-averaged Q-learning for better RL performance.
problem Improving reinforcement learning algorithms by managing uncertainty.
method Integrates statistical inference into Q-learning through sample averaging and functional central limit theorem.
result Establishes a unified theoretical foundation for sample-averaged Q-learning.
Paper analyzes finite-time convergence of double Q-learning.
problem Overestimation issue in Q-learning.
method Finite-time analysis of double Q-learning.
result Convergence to ε-accurate neighborhood in finite iterations.
Paper establishes convergence rates and concentration bounds for stochastic approximation and reinforcement learning with Markovian noise.
problem Analyzing convergence rates and concentration bounds for stochastic approximation and reinforcement learning with Markovian noise.
method Novel discretization of the mean ODE of stochastic approximation algorithms using intervals with diminishing length.
result First almost sure convergence rate and maximal concentration bound with exponential tails for contractive stochastic approximation algorithms with Markovian noise.
Q(Δ)-Learning improves Q-Learning by separating action-value functions into different time scales.
problem Q-Learning struggles with bias-variance trade-off, especially in long-term rewards.
method Introduces Q(Δ)-Learning, extending TD(Δ) to decompose Q(Δ)-function into distinct discount factors. result Q(Δ)-Learning achieves better stability and scalability, especially for long-term tasks. Continuous-time Q-learning theory developed for reinforcement learning.
problem Continuous-time reinforcement learning challenges.
method Entropy-regularized, exploratory diffusion process formulation; first-order approximation of Q-function; martingale conditions.
result Developed a q-learning theory independent of time discretization.
Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that data collection in RL is both more time and cost consuming and Q-learning converge…
This paper tackles fair same-day delivery service by optimizing regional service rates.
problem Fairness in same-day delivery service for different neighborhoods.
method Partition service area into regions, use multi-objective Markov decision process and deep Q-learning.
result Our approach maximizes fairness across all regions while maintaining overall service rate.
Unified q-learning for mean-field jump-diffusion models with unobservable population distribution.
problem Continuous-time q-learning in mean-field jump-diffusion models with unobservable population distribution.
method Proposed decoupled Iq-function for unified policy evaluation in MFG and MFC problems; unified q-learning algorithm based on test policies and averaged martingale orthogonality condition.
result Unified policy evaluation rule for MFG and MFC problems based on decoupled Iq-function.
Tabular Q-learning outperforms advanced RL methods in monetary policy.
problem Dynamic setting of short-term interest rates to stabilize inflation and unemployment under uncertain macroeconomic conditions.
method Discrete-action Markov Decision Process with tabular Q-learning, SARSA, Actor-Critic, Deep Q-Networks, Bayesian Q-learning, POMDP formulations.
result Standard tabular Q-learning achieved the best performance (-615.13 +- 309.58 mean return) compared to advanced RL methods and traditional policy rules.
This paper concerns automated vehicles negotiating with other vehicles, typically human driven, in crossings with the goal to find a decision algorithm by learning typical behaviors of other vehicles. The vehicle observes distance and speed of vehicles on the intersecting road and use a policy that adapts its speed alo…
Stochastic Q-learning tackles large action spaces with reduced computation.
problem Effective decision-making in complex environments with large discrete action spaces.
method Stochastic value-based RL approaches that consider a sublinear number of actions in each iteration.
result Stochastic Q-learning achieves near-optimal returns with significantly reduced computation time.
Study explores algorithmic collusion in repeated games using various learning dynamics.
problem Understanding algorithmic collusion in repeated games with different learning dynamics.
method Examines Q-learning, gradient learning, and other dynamics in a general repeated game setting. result Characterizes the set of payoff vectors achievable by these dynamics, revealing possibilities for collusion.
Double Q-learning has the same mean-squared error as Q-learning under certain conditions.
problem Comparing the mean-squared error of Double Q-learning and Q-learning.
method Theoretical analysis based on Lyapunov equations for both tabular and linear function approximation settings.
result The asymptotic mean-squared error of Double Q-learning is exactly equal to that of Q-learning under specific conditions.
Study evaluates reinforcement learning for trading diverse stocks, finds Q-learning outperforms.
problem Evaluating reinforcement learning for trading diverse stocks.
method Implemented Value Iteration (VI), State-action-reward-state-action (SARSA), and Q-Learning on a diverse stock portfolio dataset.
result Q-learning performs better than VI and SARSA during testing, but performance varies based on market conditions.
The paper analyzes Q-learning convergence rates with asynchronous updates.
problem Analyzing convergence rates of asynchronous Q-learning algorithms.
method Derives rates of convergence using high-dimensional central limit theorems.
result Establishes a rate of order up to n−1/6log4(nSA) for hyper-rectangles. Bayesian ATM improves stability and efficiency in mobile health interventions.
problem Balancing intervention efficacy with user burden in mobile health interventions.
method Bayesian extension to ATM using Kalman filter-style updates.
result Bayesian ATM achieves comparable or improved scalarized returns with lower variance and more stable policy behavior.