Online random forests improve Q-learning performance in specific gym environments.
problem Improving Q-learning performance in reinforcement learning tasks.
method Proposed online random forests as Q-function approximators and growing them as learning progresses.
result Improved performance over state-of-the-art Deep Q-Networks in specific gym environments.
The paper proposes a method to infer Q-values online with Q-Learning.
problem High variance and instability in reinforcement learning algorithms.
method Adapting FCLT for a modified Q-learning approach and constructing confidence intervals.
result The proposed method provides more stable and reliable inference of Q-values.
PQ-learning improves Q-learning by periodically updating target estimates.
problem Improving sample complexity in Q-learning for finding optimal policies.
method Maintains two Q-value estimates, one online and one target, updated periodically.
result PQ-learning achieves better sample complexity for finding epsilon-optimal policies.
Improved online Q-learning for MDPs with concentration bounds.
problem Online Q-learning in infinite-horizon discounted MDPs with sublinear regret for large gaps.
method Smoothed ε n ε_n ε n -Greedy exploration scheme combining ε n ε_n ε n -greedy and Boltzmann exploration, analyzed using concentration bounds for contractive Markovian stochastic approximation. result Near- i l d e O ( N 9 / 10 ) ilde{O}(N^{9/10}) i l d e O ( N 9/10 ) regret bound for Smoothed ε n ε_n ε n -Greedy exploration scheme. SafeQ-Learning uses Wasserstein DRO to ensure safety in online learning.
problem Ensuring safety in online Q-Learning algorithms.
method DrQ algorithm that uses Wasserstein ambiguity sets and offset variables.
result SafeQ-Learning provides idealistic probabilistic safety guarantees.
Paper proposes methods to handle missing data in online RL, improving efficiency and uncertainty capture.
problem Missing data in online RL poses challenges due to the need to impute and act at each time step.
method Proposes fully online imputation ensembles and multiple imputation pathways to balance uncertainty and efficiency.
result Preliminary evidence suggests multiple imputation pathways can be a useful framework for simple and efficient online missing data RL methods.
New Q-learning methods improve sample complexity for MDPs with continuous states.
problem Challenges in MDPs with continuous state spaces.
method Two nearest neighbor Q-learning methods with improved sample complexities.
result Minimax optimal sample complexities for offline and online settings.
Pretraining reinforcement learning methods with demonstrations has been an important concept in the study of reinforcement learning since a large amount of computing power is spent on online simulations with existing reinforcement learning algorithms. Pretraining reinforcement learning remains a significant challenge i…
Study Q-learning with averaging for reinforcement learning, proving efficient inference and error bounds.
problem Efficient inference and error bounds for Q-learning with averaging.
method Functional central limit theorem and asymptotic linear estimator for optimal Q-value function.
result Standardized partial-sum process converges weakly to a rescaled Brownian motion, matching instance-dependent lower bound for error.
Policy gradient is an efficient technique for improving a policy in a reinforcement learning setting. However, vanilla online variants are on-policy only and not able to take advantage of off-policy data. In this paper we describe a new technique that combines policy gradient with off-policy Q-learning, drawing experie…
Optimistic Q-learning reduces sample complexity for systems with known dynamics.
problem Sample efficiency in reinforcement learning with partial dynamics knowledge.
method Optimistic Q-learning algorithm for systems with additive disturbance model.
result Achieves i l d e O ( e x t P o l y ( H ) T ) ilde{\mathcal{O}}( ext{Poly}(H)\sqrt{T}) i l d e O ( e x t P o l y ( H ) T ) regret under perfect knowledge of dynamics. A new algorithm SRG-DQN reduces variance in deep Q-learning.
problem Inaccurate estimation of anchor points in SVRG for deep Q-learning.
method Introduces recursive gradient variance reduction for stochastic gradient updates.
result Demonstrates improved efficiency and effectiveness of SRG-DQN on reinforcement learning tasks.
SPQR improves Q-ensemble diversity in reinforcement learning.
problem Overestimation bias in Q-learning for complex tasks.
method Introduces SPQR for Q-ensemble independence regularization.
result SPQR outperforms baseline algorithms in online and offline RL benchmarks.
QPLEX learns efficient multi-agent Q-values by enforcing IGM principle.
problem Scalable multi-agent reinforcement learning with IGM consistency.
method Dueling duplex network architecture to enforce IGM principle.
result QPLEX achieves high sample efficiency and benefits from offline data.
A novel Q-learning algorithm connects information theory to MPC, improving control tasks.
problem Combining model-free RL and MPC for real-world systems with expensive queries and uncertain dynamics.
method Developed a Q-learning algorithm that uses entropy regularization and leverages biased models.
result Improves control performance on sim-to-sim tasks compared to optimal control and RL from scratch.
Transfer learning significantly accelerates the reinforcement learning process by exploiting relevant knowledge from previous experiences. The problem of optimally selecting source policies during the learning process is of great importance yet challenging. There has been little theoretical analysis of this problem. In…
Paper improves RL algorithms with known optimal Q-value predictions.
problem Improving RL algorithms with known optimal Q-value predictions.
method Shows how to improve regret bounds by distilling known optimal Q-value predictions.
result Achieves sublinear regret with known predictions, even if not distillation.
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…
Study shows offline RL under Q ⋆ Q^\star Q ⋆ -approximation and partial coverage is harder than previously thought.
problem Theoretical limits of offline reinforcement learning under Q ⋆ Q^\star Q ⋆ -approximation and partial coverage. method Introduced a decision-estimation framework to decompose offline RL complexity into decision and value estimation errors.
result Answered the open question by proving sample inefficiency under partial coverage is not guaranteed by Q ⋆ Q^\star Q ⋆ -realizability and Bellman completeness. Deep reinforcement learning (DRL) has gained a lot of attention in recent years, and has been proven to be able to play Atari games and Go at or above human levels. However, those games are assumed to have a small fixed number of actions and could be trained with a simple CNN network. In this paper, we study a special …
In an episodic Markov Decision Process (MDP) problem, an online algorithm chooses from a set of actions in a sequence of H H H trials, where H H H is the episode length, in order to maximize the total payoff of the chosen actions. Q-learning, as the most popular model-free reinforcement learning (RL) algorithm, directly pa…
Optimizes mobile notifications for multiple objectives using reinforcement learning.
problem Optimizing mobile notification systems for multiple objectives.
method End-to-end offline reinforcement learning with Double Deep Q-network and Conservative Q-learning.
result Demonstrates improved performance and benefits of the proposed approach.
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.
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.
Paper analyzes Q-learning with neural networks, proving a fast convergence rate.
problem Analyzing the convergence rate of neural Q-learning.
method Finite-time analysis of neural Q-learning with a deep ReLU network.
result Neural Q-learning converges to optimal policy with O ( 1 / T ) O(1/\sqrt{T}) O ( 1/ T ) rate. DE-QT detects optimal Q-learning stopping points.
problem Information loss in Q-learning during prolonged training.
method Introducing DE-QT to detect entropy changes in Q-tables.
result DE-QT identifies the best stopping point for Q-learning.
New method learns credit prices offline without interaction.
problem Dynamic pricing of consumer credit.
method Offline deep reinforcement learning with Q-Learning.
result Effective personalized pricing policy learned without online interaction.
This paper analyzes momentum Q-learning with finite-sample guarantees.
problem Improving Q-learning performance with momentum schemes.
method Proposes MomentumQ algorithm integrating Nesterov and Polyak's momentum schemes, analyzes convergence for function approximations.
result Establishes finite-sample convergence rates for MomentumQ, demonstrating better performance than vanilla Q-learning.
EBQL reduces bias in Q-learning for improved performance.
problem Over- and under-estimation biases in Q-learning degrade performance.
method Ensemble Bootstrapping to reduce both over- and under-estimation biases.
result EBQL outperforms other Q-learning methods in Atari games.
New self-imitation learning method improves performance in continuous control tasks.
problem Improving off-policy learning in continuous control tasks.
method Proposes a n-step lower bound to generalize lower-bound Q-learning and introduces a new family of self-imitation learning algorithms.
result n-step lower bound Q-learning achieves a better trade-off between bias and contraction rate, leading to improved performance.
Linear Q-learning converges to a bounded set without divergence.
problem Proving linear Q-learning does not diverge and converges to a bounded set.
method No modifications to the original linear Q-learning algorithm, no Bellman completeness or near-optimality assumptions, only an ε-softmax behavior policy with adaptive temperature.
result First L 2 L^2 L 2 convergence rate of linear Q-learning iterates to a bounded set. Proposes a RL method using simulators for stabilizing uncertain systems.
problem Limited experiences and potential dangerous actions during RL learning of real systems.
method Two-stage approach: virtual systems for Q-function learning, real system interactions for final policy.
result Proposed method improves RL performance in uncertain discrete-time systems.
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 σ σ ) algorithm (Sutton and Barto (2017)) unifies both. This paper extends the Q( σ σ σ ) algorithm to an online multi-step algorithm Q( σ , λ σ, λ σ , λ ) using eligibility traces and int…
Q-learning requires more samples than minimax bounds suggest for optimal Q-function approximation.
problem Understanding the sample complexity of Q-learning in synchronous settings.
method Analyzing Q-learning in synchronous MDPs with state and action spaces, proving minimax optimal sample complexity for TD learning and Q-learning under certain conditions.
result Q-learning requires more samples than minimax bounds suggest, revealing strict sub-optimality when action space is more than one.
Q-learning for average cost MDPs gets a concentration bound.
problem Finding bounds for Q-learning in average cost MDPs.
method Derives a concentration bound using shortest path problem equivalence.
result Numerical comparison with relative value iteration shows the bound's effectiveness.
New algorithm uses Whittle index to improve Q-learning for restless bandits.
problem Optimizing decision-making in multiarmed restless bandits with average reward.
method Introduces a novel reinforcement learning algorithm combining Q-learning and Whittle index policy.
result Demonstrates significant computational gains and excellent empirical performance.
One-step Bellman alignment improves online RL by reducing task mismatch.
problem Online RL struggles with task similarity defined by rewards or transitions.
method One-step Bellman alignment and re-weighted targeting (RWT) to correct task mismatch.
result Regret bounds show task shift complexity, not target MDP, affects performance.
LBQL improves Q-learning by using lookahead bounds for better performance.
problem Improving Q-learning in stochastic environments.
method LBQL uses lookahead bounds to construct dual penalties and track upper and lower bounds via stochastic approximation.
result LBQL converges faster and is more robust to hyperparameters than standard Q-learning.
This paper analyzes how periodic and soft target updates stabilize linear Q-learning.
problem Theoretical explanation of stabilization mechanisms for linear Q-learning.
method Exact analysis using switched linear system dynamics and the joint spectral radius.
result Periodic and soft target updates can guarantee convergence to the exact projected Q-Bellman solution under specific conditions.
FedLCB-Q learns optimal policies from federated offline data with linear speedup.
problem Learning optimal policies from offline data with federated learning.
method Federated offline RL algorithm tailored for Q-learning, using local Q-function updates and central aggregation.
result Achieves linear speedup in sample complexity with collaboration among agents.
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.
Paper addresses underestimation bias in double Q-learning, proposing a method to improve learning performance.
problem Underestimation bias in double Q-learning leading to non-optimal fixed points.
method Proposes a simple approach using approximate dynamic programming to bound the target value.
result Significant improvement in learning performance over baseline algorithms in Atari benchmark tasks.
Paper presents a deep reinforcement learning algorithm for online trading without offline training.
problem Developing a fully online trading algorithm without offline training.
method Double Deep Q Q Q -learning with Fast Learning Networks, defining terminal states for money conservation. result The algorithm outperforms random action trading and captures different market trends.
New algorithm reduces sample and communication complexities in federated Q-learning.
problem Optimal Q-function learning in federated Q-learning with limited communication.
method Introduced Fed-DVR-Q algorithm for order-optimal sample and communication complexities.
result Complete characterization of sample-communication complexity trade-off.
This paper improves Q-learning bounds using reference-advantage decomposition.
problem Improving Q-learning bounds in MDPs with positive suboptimality gaps.
method Develops a novel error decomposition framework to prove gap-dependent regret bounds.
result Establishes logarithmic gap-dependent regret bounds for Q-learning.
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.
Extended analysis of Q-learning's efficiency, matching optimal regret.
problem Theoretical guarantees of Q-learning's efficiency and optimal regret.
method Survey of related research, detailed proof reasoning.
result Q-learning with UCB exploration achieves sample efficiency matching optimal regret.
Proposes a new Q-learning method for survival outcomes in clinical trials.
problem Incomplete follow-up data and nonlinear covariate effects in clinical trials.
method Combines Buckley-James boosting with flexible base learners for estimating optimal treatment regimes.
result Improves treatment decision accuracy and stability in longitudinal clinical trials.