Efficient RL for linear MDPs with unknown transitions.
problem Long planning horizons and unknown state transitions in linear mixture MDPs.
method Horizon-free algorithm using weighted least squares with variance and uncertainty awareness.
result Achieves optimal regret up to logarithmic factors.
Paper proposes a privacy-preserving RL algorithm for linear MDPs with theoretical guarantees.
problem Protecting users' private data in personalized services using RL.
method Local differential privacy (LDP) for RL with linear function approximation.
result Achieves a regret bound of $O(d^{5/4}H^{7/4}T^{3/4}\left(\log(1/δ)
ight)^{1/4}\sqrt{1/\varepsilon})$ for linear mixture MDPs.
Algorithm learns mixtures of Markov chains and MDPs from short trajectories.
problem Learning mixtures of Markov chains and MDPs from short unlabeled trajectories.
method Subspace estimation, spectral clustering, EM algorithm, model estimation, classification.
result 96.6% average accuracy on a mixture of two MDPs in gridworld, outperforming EM algorithm with random initialization.
We study Exo-MDPs to reduce sample complexity in reinforcement learning.
problem Reducing sample complexity in reinforcement learning for structured MDPs.
method Introducing Exo-MDPs and proving structural equivalence to linear mixture MDPs, establishing regret bounds.
result Proved O ( H 3 / 2 d K ) O(H^{3/2}d\sqrt{K}) O ( H 3/2 d K ) regret bound for Exo-MDPs, matching lower bounds. New algorithm reduces reinforcement learning regret for linear MDPs with unknown transitions.
problem Adversarial linear mixture MDPs with bandit feedback and unknown transition.
method Proposes a new algorithm with a least square estimator and self-normalized concentration.
result Achieves improved regret bound with high probability.
Algorithm learns from offline data to improve performance in target environment.
problem Learning from offline data in a target environment with unknown shifts.
method Adaptive algorithm that uses offline data to improve performance when informative.
result Algorithm provably improves performance over purely online learning when offline data are informative.
Significant improvements in regret analysis for adaptive online learning problems.
problem Exploiting low variance in online learning problems without known variances.
method Novel peeling-based regret analysis leveraging elliptical potential `count` lemma.
result Significant improvements in regret bounds for linear bandits and linear mixture MDPs.
Enhances RL with function approximation, improving regret bounds.
problem Improving exploration in reinforcement learning with function approximation.
method Prior-dependent Bayesian regret bound for PSRL with linear mixture MDPs, using value-targeted model learning and variance reduction.
result Established an upper bound of O ( d H 3 T log T ) {\mathcal{O}}(d\sqrt{H^3 T \log T}) O ( d H 3 T log T ) for PSRL. New algorithm reduces dynamic regret for MDPs with unknown transition and adversarial rewards.
problem Episodic linear mixture MDPs with unknown transition and adversarial rewards.
method Combines occupancy-measure-based global optimization and policy-based variance-aware value-targeted regression.
result Achieves near-optimal dynamic regret of O ~ ( d H 3 K + H K ( H + P ˉ K ) ) \widetilde{\mathcal{O}}(d \sqrt{H^3 K} + \sqrt{HK(H + \bar{P}_K)}) O ( d H 3 K + H K ( H + P ˉ K ) ) . New RL algorithm for linear MDPs with nearly optimal regret.
problem Optimizing reinforcement learning for linear mixture Markov decision processes.
method Proposed a new Bernstein-type concentration inequality for self-normalized martingales and a computationally efficient algorithm UCRL-VTR+.
result UCRL-VTR+ achieves nearly minimax optimal regret of i l d e O ( d H T ) ilde O(dH\sqrt{T}) i l d e O ( d H T ) . Logarithmic regret achieved in RL with linear function approximation.
problem Achieving logarithmic regret in reinforcement learning with linear function approximation.
method LSVI-UCB for linear MDP assumption, UCRL-VTR for linear mixture MDP assumption.
result Logarithmic regret bounds established for RL with linear function approximation.
Paper optimizes learning MDPs with adversarial rewards using linear models.
problem Learning MDPs with adversarial rewards and changing reward functions.
method Proposes POWERS, an optimistic policy optimization algorithm.
result Achieves nearly optimal regret bound of O ( d H T ) O(dH\sqrt{T}) O ( d H T ) . New algorithm reduces regret for linear bandits with unknown noise variance.
problem Finding optimal actions in linear bandits with varying noise variance.
method Adaptive algorithm with Freedman-type concentration inequality and multi-layer structure.
result Achieves i l d e O ( d ∑ k = 1 K σ k 2 + d ) ilde{O}(d \sqrt{\sum_{k = 1}^K σ_k^2} + d) i l d e O ( d ∑ k = 1 K σ k 2 + d ) regret for linear bandits. New algorithm learns policies without explicit rewards for MDPs.
problem Learning policies for MDPs without explicit rewards.
method UCRL-RFE algorithm with linear function approximation.
result UCRL-RFE achieves optimal policy with minimal exploration samples.
New method for optimistic planning in MDPs using regularization.
problem Optimistic planning in infinite-horizon discounted MDPs.
method Regularized dynamic programming for approximate value iteration.
result Achieves near-optimal statistical guarantees in learning policies.
New algorithm for RL with horizon-free reward-free exploration for linear MDPs.
problem Reward-free reinforcement learning with long planning horizons.
method Uncertainty-weighted value-targeted regression with exploration-driven pseudo-reward and moment estimator.
result Horizon-free sample complexity of O ( d 2 ε − 2 ) O(d^2\varepsilon^{-2}) O ( d 2 ε − 2 ) for finding an ε \varepsilon ε -optimal policy. This paper refines the weighted strategy for non-stationary parametric bandits and MDPs, improving regret bounds.
problem Non-stationary environments with gradual drifting patterns.
method Refined analysis framework for the weighted strategy, leading to simpler and more efficient algorithms.
result Improved regret bounds for linear bandits, generalized linear bandits, and self-concordant bandits.
A new framework for robust policy learning in MDPs with linear mixture dynamics.
problem Off-dynamics challenge in real-world decision-making problems.
method Linear mixture DRMDP framework, meta algorithm for robust policy learning.
result The new framework provides a more refined representation of uncertainties.
Proposes a Riemannian optimization for policy improvement in MDPs.
problem Optimizing policy functions in Markov decision processes (MDPs).
method Riemannian proximal optimization algorithm with Gaussian mixture model (GMM).
result Guaranteed convergence and efficacy demonstrated in preliminary experiments.
New algorithm tackles adversarial RL without horizon constraints.
problem Adversarial reinforcement learning with unknown transition kernel.
method Uses weighted least square estimator and occupancy measure for policy search.
result Achieves near-optimal regret bound of O ( K ) O(\sqrt{K}) O ( K ) . Improved regret bound for MNL MDPs with variance-aware approach.
problem Optimal reinforcement learning for MNL MDPs with structured variance.
method Introducing a problem-dependent constant measuring average variance, proposing an algorithm with improved regret bound.
result Minimax optimal regret bound of O ( d H 2 σ ˉ T T ) O(dH^2\barσ_T\sqrt{T}) O ( d H 2 σ ˉ T T ) for structured MDPs. New framework allows reinforcement learning with polynomial sample complexity.
problem Generalization in reinforcement learning with function approximation.
method Introduces Bilinear Classes, a structural framework for RL.
result Polynomial sample complexity for Bilinear Classes, matching best known bounds.
We study the problem of learning policy of an infinite-horizon, discounted cost, Markov decision process (MDP) with a large number of states. We compute the actions of a policy that is nearly as good as a policy chosen by a suitable oracle from a given mixture policy class characterized by the convex hull of a set of k…
New RL method learns to skip states in linearly q π q^π q π -realizable MDPs, simplifying to linear MDPs.
problem Online RL in episodic MDPs with linearly q π q^π q π -realizable action-values. method Derives a novel algorithm that learns to skip states and applies a linear MDP algorithm.
result First polynomial-sample-complexity online RL algorithm for linearly q π q^π q π -realizable MDPs. Optimistic PPO variant solves linear MDPs with improved regret bound.
problem Understanding theoretical limits of PPO in linear MDPs.
method Proposes an optimistic variant of PPO for episodic adversarial linear MDPs with full-information feedback.
result Establishes a i l d e O ( d 3 / 4 H 2 K 3 / 4 ) ilde{\mathcal{O}}(d^{3/4}H^2K^{3/4}) i l d e O ( d 3/4 H 2 K 3/4 ) regret bound. New method tackles MDPs by learning normalized representations efficiently.
problem Curse of dimensionality in MDPs.
method Contrastive representation learning for linear MDPs.
result First practical method with strong theoretical guarantees and empirical performance.
New RL approach tackles non-linear MDPs without linear assumptions.
problem Sample efficiency in RL for complex, nonlinear MDPs with continuous states.
method Introduces EPW condition to relax linear structure requirements; provides sample-efficient RL algorithm.
result EPW condition allows solving MDPs without linear assumptions, including Atari games.
The paper establishes a nearly-sharp statistical threshold for efficient learning in Latent MDPs with separated components.
problem Learning Latent Markov Decision Processes (LMDPs) with separated components.
method The paper considers various notions of separation and establishes a nearly-sharp statistical threshold for efficient learning. It also presents a quasi-polynomial algorithm with time complexity scaling in terms of the statistical threshold under a weaker assumption of separability under the optimal policy, and a near-matching time complexity lower bound under the exponential time hypothesis.
result Establishes a nearly-sharp statistical threshold for efficient learning in Latent MDPs with separated components.
Policy gradient methods achieve linear convergence in simple MDPs.
problem Analyzing convergence rates of policy gradient methods in finite MDPs.
method Connections with policy iteration to show linear convergence with large step-sizes.
result Policy gradient methods succeed with large step-sizes and achieve linear rate of convergence.
The paper addresses statistical estimation in MDPs with confounders using instrumental variables.
problem Statistical estimation of value functions in MDPs with unobservable confounders.
method Two-stage estimator based on instrumental variables for confounded linear MDPs.
result Established statistical properties of the two-stage estimator, including error bounds and asymptotic normality.
Reward-free RL in linear MDPs is as hard as reward-aware RL.
problem Reward-free RL in linear MDPs without access to the reward function during exploration.
method Developed a computationally efficient algorithm with sample complexity O ~ ( d 2 H 5 / ε 2 ) \widetilde{\mathcal{O}}(d^2 H^5/ε^2) O ( d 2 H 5 / ε 2 ) . result Achieved optimal d d d dependence in linear MDPs for reward-free RL, matching the reward-aware RL setting. Efficiently plans large MDPs with weak function approximations.
problem Planning in large MDPs with limited function approximation capabilities.
method Uses linear value function approximation with weak requirements and a generative oracle.
result Produces almost-optimal actions for any state with polynomial computation time.
New algorithm for offline RL with linear approx in MDPs and MGs, nearly optimal.
problem Offline RL with linear function approximation in MDPs and MGs.
method Pessimism-based algorithm with uncertainty decomposition via reference function.
result Nearly minimax optimal performance in offline RL for MDPs and MGs.
New algorithms solve robust MDPs efficiently, significantly faster than existing methods.
problem Computing robust MDP solutions with uncertainty in transition probabilities is computationally expensive.
method Partial policy iteration and fast robust Bellman operator computation methods.
result The proposed methods are many orders of magnitude faster than state-of-the-art approaches.
Improved RL algorithm with linear MDPs for offline learning with partial data coverage.
problem Efficient offline RL with linear MDPs under partial data coverage.
method Primal-dual algorithm with O ( ε − 2 ) O(ε^{-2}) O ( ε − 2 ) sample complexity. result First computationally efficient algorithm with O ( ε − 2 ) O(ε^{-2}) O ( ε − 2 ) sample complexity for offline RL with linear MDPs under partial data coverage. DARLING tackles non-stationary RL with guarantees, improving dynamic regret.
problem Non-stationary reinforcement learning in unknown change points.
method Detection Augmented Reinforcement Learning (DARLING) for tabular and linear MDPs.
result DARLING matches minimax lower bounds in tabular and linear MDPs.
UCRL2-VTR achieves nearly optimal regret for learning MDPs with linear function approximation.
problem Learning infinite-horizon average-reward MDPs with linear function approximation.
method UCRL2-VTR algorithm with Bernstein-type bonus.
result Achieves a regret of i l d e O ( d D T ) ilde{O}(d\sqrt{DT}) i l d e O ( d D T ) with matching lower bound. New RL algorithm tackles nonstationary MDPs with linear approximations and varying rewards.
problem Nonstationary reinforcement learning with evolving reward and state transition functions.
method Developed a new algorithm LSVI-UCB-Restart with periodic restart, and parameter-free Ada-LSVI-UCB-Restart for unknown variation budgets.
result First minimax dynamic regret lower bound for nonstationary linear MDPs and linear MDPs lower bound.
New algorithm learns sparse linear MDPs with polynomial interactions, improving sample complexity.
problem Learning optimal policies in sparse linear MDPs with limited interactions and unknown features.
method Developed a polynomial-time algorithm using feature selection and emulator for sparse linear MDPs.
result First polynomial-time algorithm for learning near-optimal policies in k-sparse linear MDPs.
Extends linear MDP to handle nonlinear rewards.
problem Restrictive linear MDP assumption limits real-world applicability.
method Proposes Generalized Linear MDP (GLMDP) with GLMs for rewards.
result Develops offline RL algorithms achieving suboptimality guarantees.
Trajectory data suffices for efficient RL in linear MDPs.
problem Efficient offline RL in linear MDPs without state space scaling.
method Linear MDP approximation and trajectory data.
result Trajectory data suffices for deriving ε-optimal policies.
New algorithm reduces switching costs in RL beyond linear MDPs.
problem Costly policy switching in reinforcement learning.
method ELEANOR-LowSwitching algorithm for linear Bellman-complete MDPs.
result Achieves near-optimal regret with logarithmic switching cost.
ARL-GEN adapts to the smallest model class in nested families for RL with improved regret.
problem Model selection for Reinforcement Learning with nested model families.
method Adaptive Reinforcement Learning (ARL-GEN) with value targeted regression and model selection module.
result ARL-GEN achieves a matching regret to an oracle with knowledge of the true model class.
New RL algorithm achieves nearly optimal performance for linear MDPs.
problem Optimal reinforcement learning for episodic linear MDPs.
method Weighted linear regression with variance estimator and rare-switching policy.
result Achieves nearly minimax optimal regret i l d e O ( d H 3 K ) ilde O(d\sqrt{H^3K}) i l d e O ( d H 3 K ) . Quantum RL algorithm achieves logarithmic regret for exploration.
problem Designing efficient quantum RL algorithms for exploration.
method UCRL-style quantum algorithm with lazy updating and quantum estimation.
result Proves O ( p o l y ( S , A , H , log T ) ) \mathcal{O}(\mathrm{poly}(S, A, H, \log T)) O ( poly ( S , A , H , log T )) worst-case regret. In this paper we derive an efficient method for computing the indices associated with an asymptotically optimal upper confidence bound algorithm (MDP-UCB) of Burnetas and Katehakis (1997) that only requires solving a system of two non-linear equations with two unknowns, irrespective of the cardinality of the state spac…
Hybrid RL algorithms improve offline and online RL in linear MDPs.
problem Improving RL performance without single-policy concentrability.
method Developed computationally efficient algorithms for PAC and regret-minimizing RL in linear MDPs.
result Achieved sharper error or regret bounds for linear MDPs.
While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and position contains configurations that are not physically reachable). This leads to defining weakly-communicating or multi-chain MDPs. In this…