Paper proves convergence of optimistic policy iteration for stochastic shortest path problems.
problem Optimizing policies in stochastic shortest path problems.
method Analyzes optimistic policy iteration algorithm with Monte Carlo and TD(λ) methods.
result Proves convergence of the algorithm under specific conditions.
Accelerates policy optimization in RL with optimistic and adaptive updates.
problem Improving policy optimization methods in reinforcement learning.
method Integrates foresight into policy improvement step via optimistic and adaptive updates.
result Designs an optimistic policy gradient algorithm, adaptive via meta-gradient learning.
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.
Algorithm converges to Nash equilibria in competitive games.
problem Finding Nash equilibria in decentralized, competitive Markov games.
method Decentralized Optimistic Gradient Descent/Ascent with a critic.
result Converges to the set of Nash equilibria under self-play.
PROPO tackles non-stationary MDPs with efficient policy optimization.
problem Non-stationary MDPs with varying reward and transition kernels.
method PROPO, a periodic restarted optimistic policy optimization algorithm with sliding-window-based policy evaluation and improvement.
result PROPO achieves near-optimal performance in non-stationary MDPs.
New algorithm reduces reinforcement learning regret to sqrt(T) without strong dynamics assumptions.
problem Infinite-horizon average-reward reinforcement learning with linear MDPs.
method Approximate by discounted-reward MDPs and apply optimistic value iteration.
result Achieves O(sqrt(T)) regret with polynomial complexity.
Optimistic NPG improves policy optimization in online RL with efficient sample complexity.
problem Limited theoretical understanding of policy optimization, especially in online RL.
method Combines natural policy gradient with optimistic policy evaluation.
result Achieves optimal dimension dependence sample complexity for learning near-optimal policies.
New algorithm reduces regret in sequential decision-making problems.
problem Balancing exploration and exploitation in online sequential decision problems.
method Variational Bayesian optimistic sampling (VBOS) for optimizing policies.
result VBOS achieves i l d e O ( A T ) ilde O(\sqrt{AT}) i l d e O ( A T ) Bayesian regret for stochastic multi-armed bandits. Develops ODRPO to improve RL algorithms with better performance and stability.
problem RL algorithms converge to sub-optimal solutions due to limited policy representation.
method Integrates DRO approach to solve trust region constrained optimization problem without parameterizing policies.
result Achieves globally optimal policy update and higher sample efficiency.
Enhances reinforcement learning safety through risk-averse exploration.
problem Safety concerns in reinforcement learning due to sub-optimal actions.
method Distributionally robust policy iteration scheme with lower bound guarantees.
result Efficient algorithm that prevents poor decisions and converges to optimal policy.
Optimistic actor-critic tackles linear MDPs with parametric policies.
problem Theoretical limitations of existing actor-critic methods for linear MDPs.
method Proposes an optimistic actor-critic framework with parametric log-linear policies and approximate Thompson sampling.
result Achieves state-of-the-art sample complexity in both on-policy and off-policy settings.
AAPI improves regret bound for undiscounted continuing learning in uniformly ergodic MDPs.
problem Improving regret bounds for undiscounted continuing learning in uniformly ergodic MDPs.
method Adaptive approximate policy iteration (AAPI) with online learning techniques and data-dependent adaptive learning rate.
result AAPI achieves a i l d e O ( T 2 / 3 ) ilde{O}(T^{2/3}) i l d e O ( T 2/3 ) regret bound, improving over the best existing bound of i l d e O ( T 3 / 4 ) ilde{O}(T^{3/4}) i l d e O ( T 3/4 ) . 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 algorithm identifies near-optimal policies in adversarial distributed RL settings.
problem Adversarial agents in distributed RL settings that can collude and report arbitrary data.
method Weighted-Clique algorithm for robust mean estimation from batches, combined with novel distributed algorithms.
result Achieves superior robustness guarantees and near-optimal sample complexities in both offline and online settings.
New rule reduces exploration regret to logarithmic, improving bad episode handling.
problem Improving exploration regret in average reward MDPs.
method Replacing Doubling Trick with Vanishing Multiplicative rule in EVI-based algorithms.
result Regret is logarithmic under the new rule, significantly better than linear.
Proposes H-UCRL for efficient model-based RL with sublinear regret.
problem Greedy policy exploration in model-based RL ignores epistemic uncertainty.
method Reparameterizes plausible models, hallucinates control, augments input space, solves with greedy planners.
result H-UCRL achieves provably sublinear regret for Gaussian Process models.
New RL algorithm optimizes policies with bandit feedback, matching previous bounds.
problem Optimizing policies with unknown transitions and bandit feedback.
method Optimistic Trust Region Policy Optimization (TRPO) algorithm.
result Sub-linear regret bounds for both stochastic and adversarial rewards.
New method for robust policy evaluation in offline reinforcement learning with sequentially exogenous unobserved confounders.
problem Offline reinforcement learning in domains with unobserved confounders.
method Orthogonalized robust fitted-Q-iteration with closed-form solutions and bias-correction.
result Effective in simulations and real-world data, improving robustness and computational ease.
New method minimizes regret in AMDP with high probability.
problem Pessimistic regret analysis in AMDP.
method Developed a new policy search method achieving optimistic regret.
result Achieved sublinear optimistic regret with high probability.
Optimistic algorithm reduces regret in non-stationary linear MDPs.
problem Efficient learning in non-stationary linear MDPs with evolving reward and transition.
method OPT-WLSVI, an optimistic model-free algorithm using exponential weights.
result Achieves a regret bound of O ~ ( d 5 / 4 H 2 Δ 1 / 4 K 3 / 4 ) \widetilde{\mathcal{O}}(d^{5/4}H^2 Δ^{1/4} K^{3/4}) O ( d 5/4 H 2 Δ 1/4 K 3/4 ) . OPPO optimizes policy learning with provable efficiency.
problem Designing efficient policy optimization algorithms that incorporate exploration.
method Proposes an Optimistic Proximal Policy Optimization (OPPO) algorithm.
result Achieves i l d e O ( d 2 H 3 T ) ilde{O}(\sqrt{d^2 H^3 T} ) i l d e O ( d 2 H 3 T ) regret in episodic MDPs. Online Apprenticeship Learning aims to match expert performance without access to cost functions.
problem Learning an agent's policy to match expert performance in an MDP without cost function access.
method Combines mirror descent based no-regret algorithms for policy optimization and cost learning, with optimistic exploration.
result Derives an algorithm with O ( K ) O(\sqrt{K}) O ( K ) regret, practical for high-dimensional control problems. Optimistic method adapted for faster convex-concave min-max problems.
problem Solving convex-concave min-max optimization problems efficiently.
method Adaptive, line search-free second-order methods combining optimistic updates and second-order information.
result Achieves optimal convergence rate without line search or backtracking.
Efficient reinforcement learning for simultaneous-move zero-sum games using optimistic value iteration.
problem Learning optimal strategies in simultaneous-move zero-sum Markov games with function approximation.
method Developed an optimistic variant of least-squares minimax value iteration algorithm for offline and online settings.
result Achieved an upper bound of i l d e O ( d 3 H 3 T ) ilde O(\sqrt{d^3 H^3 T}) i l d e O ( d 3 H 3 T ) on duality gap and regret. New RL algorithm tackles online robust MDPs with uncertainty.
problem Developing robust reinforcement learning models for real-world environments.
method Proposes a robust optimistic policy optimization algorithm for online robust MDPs.
result Establishes the first regret bound for online robust MDPs.
Combines online learning algorithms to achieve better performance.
problem Improving online learning algorithms with varying guarantees.
method Adding iterates of two parameter-free algorithms to create a new algorithm with improved regret.
result Generates efficient algorithms that adapt to multiple norms and maintain dimension-free guarantees.
A new policy for contextual bandits adapts to reward vector shifts.
problem Learning under reward vector shifts with ordered rewards.
method Adaptive-discretization and optimistic elimination policy.
result Established upper bounds on preference-based regret.
This paper optimizes off-policy evaluation in reinforcement learning with function approximation.
problem Estimating cumulative value of a new policy from logged data generated by an unknown policy.
method Regression-based fitted Q iteration method, equivalent to estimating conditional mean embedding of transition operator.
result The method is minimax-optimal, with nearly minimal estimation error.
New batch RL method avoids overly optimistic policies.
problem Challenges in applying RL to large domains with limited data.
method Modified Bellman optimality and evaluation back-up for conservative updates.
result Can find approximately best policies within explored state-action space.
A generalized optimistic method for saddle point problems with improved complexity.
problem Solving convex-concave saddle point problems efficiently.
method Proposes a generalized optimistic method that includes the optimistic gradient method as a special case, handling constrained saddle point problems with composite objective functions and arbitrary norms.
result Best-known global iteration complexity bounds for first-, second-, and higher-order methods.
New algorithm achieves data-dependent regret bounds in MDPs with unknown transitions.
problem Achieving best-of-both-worlds guarantees with data-dependent regret bounds in MDPs with unknown transitions.
method Optimistic follow-the-regularized-leader algorithm with new optimistic Q-function estimators and transition bonus.
result First-order, second-order, and path-length bounds with polylog(T) regret in the stochastic regime.
Develops new algorithms for solving root-finding problems in large-scale settings.
problem Solving nonlinear equations in large-scale settings.
method Randomized block-coordinate optimistic gradient algorithms.
result Achieves convergence rates of O ( 1 / k ) \mathcal{O}(1/k) O ( 1/ k ) and O ( 1 / k 2 ) \mathcal{O}(1/k^2) O ( 1/ k 2 ) for root-finding problems. DORIS algorithm achieves no-regret learning in Markov games with adversarial opponents.
problem Decentralized policy learning in Markov games with nonstationary opponents.
method DORIS algorithm using optimistic hyperpolicy mirror descent.
result Achieves K \sqrt{K} K -regret in general function approximation. This paper introduces a new metric, ULI, for RL that ensures both cumulative and instantaneous performance.
problem High-stakes applications require RL algorithms to avoid playing bad policies.
method Introduces uniform last-iterate (ULI) guarantee, a stronger metric capturing both cumulative and instantaneous performance.
result ULI directly implies near-optimal cumulative performance across various metrics, but not the other way around.
OMWU shows last iterate convergence in convex-concave games.
problem Optimizing in constrained min-max optimization landscapes.
method OMWU (Optimistic Multiplicative-Weights Update) in the no-regret online learning framework.
result OMWU exhibits last iterate convergence for convex-concave games, generalizing previous results.
Study optimal policy regret in partially observable Markov games with adaptive opponents.
problem Optimal sequential decision-making in partially observable environments against strategic, adaptive opponents.
method An epoch-based optimistic maximum-likelihood algorithm that selects one policy per epoch using confidence sets built cumulatively from past data.
result Achieves i l d e O ( T ) ilde{O}(\sqrt{T}) i l d e O ( T ) policy regret for fixed problem parameters, with explicit dependence on horizon, adversary memory, confidence radius, and aggregate Eluder dimension. New NPG variants ensure parameter convergence in multi-agent learning.
problem Non-convergence of parameters in NPG for multi-agent learning.
method Proposed variants of NPG for multi-agent learning scenarios.
result Global last-iterate parameter convergence guarantees in various multi-agent learning settings.
Improved algorithm for online planning with tighter bounds.
problem Online planning in Markov Decision Processes with open-loop policies and budget constraints.
method Proposed KLOLOP algorithm with tighter upper-confidence bounds and efficient implementation.
result KLOLOP leads to better practical performances with sample complexity bound retained.
Efficiently solves exploration-exploitation in LQR using Lagrangian relaxation.
problem Exploration-exploitation dilemma in linear quadratic regulator (LQR) setting.
method Relax optimistic optimization into a constrained extended LQR problem, then solve using Riccati equations.
result Computes ε ε ε -optimistic controller efficiently with O ( log ( 1 / ε ) ) O\big(\log(1/ε)\big) O ( log ( 1/ ε ) ) Riccati equations. A framework for navigating environments with spatially correlated obstacles and uncertain blockage status.
problem Navigation in environments with spatially correlated obstacles of uncertain blockage status.
method Modeling spatial correlation with Gaussian Random Field, developing Bayesian belief updates, proposing a two-stage learning framework with offline and online phases.
result Consistent performance gains over baselines in environments with adversarial interruptions or clustered natural hazards.
We analyze reinforcement learning algorithms using a distributional approach.
problem Theoretical analysis of reinforcement learning algorithms for constant step-sizes.
method Distributional approach to theoretical analyses of reinforcement learning algorithms.
result TD( λ λ λ ) and Q Q Q -Learning have contractive update rules in the space of distributions of functions, leading to exponentially fast convergence. New analysis shows convergence rate of 1/k for gradient and extra-gradient methods.
problem Finding saddle points in convex-concave problems.
method Interpreted as proximal point method approximations, showing iterates remain bounded.
result Primal dual gap converges at rate O(1/k).
Improved POMDP regret to sqrt(T) with known observation model.
problem Average-reward POMDPs with unknown transition model but known observation model.
method Optimistic algorithm using deterministic policies and novel estimation techniques.
result First approach with regret guarantee of sqrt(T) against optimal policy.
New algorithms reduce regret in online MDPs by adapting to data and variance.
problem Adapting to both adversarial and stochastic environments in online MDPs.
method Develops algorithms based on global optimization and policy optimization, using optimistic follow-the-regularized-leader with log-barrier regularization.
result Achieves refined data-dependent and variance-dependent regret bounds.
We consider the problem of minimizing a smooth convex function by reducing the optimization to computing the Nash equilibrium of a particular zero-sum convex-concave game. Zero-sum games can be solved using online learning dynamics, where a classical technique involves simulating two no-regret algorithms that play agai…
New ODE models show saddle-point optimization methods converge differently, with last-iterate convergence for OGDA.
problem Analyzing convergence properties of saddle-point optimization methods.
method High-Resolution Differential Equations (HRDEs) to design differential equation models for saddle-point optimization methods.
result HRDEs reveal last-iterate convergence for Optimistic Gradient Descent Ascent (OGDA) in bilinear games.
We address the issue of limit cycling behavior in training Generative Adversarial Networks and propose the use of Optimistic Mirror Decent (OMD) for training Wasserstein GANs. Recent theoretical results have shown that optimistic mirror decent (OMD) can enjoy faster regret rates in the context of zero-sum games. WGANs …
Motivated by applications in Game Theory, Optimization, and Generative Adversarial Networks, recent work of Daskalakis et al \cite{DISZ17} and follow-up work of Liang and Stokes \cite{LiangS18} have established that a variant of the widely used Gradient Descent/Ascent procedure, called "Optimistic Gradient Descent/Asce…