No article text was recorded for this version.
unique optimal action assumption
Version 2 of 269 papers90 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Towards Blackwell Optimality: Bellman Optimality Is All You Can Get
- Blog: Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms
- Blog: Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap
- Blog: The best of both worlds: stochastic and adversarial episodic MDPs with unknown transition
- Blog: Non-Asymptotic Analysis of a UCB-based Top Two Algorithm
- Blog: An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits
- Blog: Phased Exploration with Greedy Exploitation in Stochastic Combinatorial Partial Monitoring Games
- Blog: Tsallis-INF for Decoupled Exploration and Exploitation in Multi-armed Bandits
- Blog: REINFORCE Converges to Optimal Policies with Any Learning Rate
- Blog: Constant Stepsize Q-learning: Distributional Convergence, Bias and Extrapolation
- Blog: Simple combinatorial algorithms for combinatorial bandits: corruptions and approximations
- Blog: Improved Analysis of the Tsallis-INF Algorithm in Stochastically Constrained Adversarial Bandits and Stochastic Bandits with Adversarial Corruptions
- Blog: Parameter-Free Multi-Armed Bandit Algorithms with Hybrid Data-Dependent Regret Bounds
- Blog: An $\varepsilon$-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond
- Blog: Identification of Blackwell Optimal Policies for Deterministic MDPs
- Blog: Best-of-Both-Worlds Algorithms for Partial Monitoring
- Blog: A Blackbox Approach to Best of Both Worlds in Bandits and Beyond
- Blog: Better Best of Both Worlds Bounds for Bandits with Switching Costs
- Blog: Online Learning of Rested and Restless Bandits
- Blog: On Optimal Robustness to Adversarial Corruption in Online Decision Problems
- Blog: Nearly Optimal Best-of-Both-Worlds Algorithms for Online Learning with Feedback Graphs
- Blog: Simultaneously Learning Stochastic and Adversarial Markov Decision Process with Linear Function Approximation
- Blog: A Near-Optimal Best-of-Both-Worlds Algorithm for Federated Bandits
- Blog: Parametric Graph for Unimodal Ranking Bandit
- Blog: An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
- Blog: Logarithmic Regret of Exploration in Average Reward Markov Decision Processes
- Blog: Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
- Blog: Why Policy Gradient Algorithms Work for Undiscounted Total-Reward MDPs
- Blog: Improved Analysis of Robustness of the Tsallis-INF Algorithm to Adversarial Corruptions in Stochastic Multiarmed Bandits
- Blog: Factored Bandits
- Blog: Combinatorial Pure Exploration with Bottleneck Reward Function and its Extension to General Reward Functions
- Blog: Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
- Blog: Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature
- Blog: Robust Knowledge Transfer in Tiered Reinforcement Learning
- Blog: Top Two Algorithms Revisited
- Blog: Almost Optimal Anytime Algorithm for Batched Multi-Armed Bandits
- Blog: Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
- Blog: Adaptive Best-of-Both-Worlds Algorithm for Heavy-Tailed Multi-Armed Bandits
- Blog: An Optimal Algorithm for Stochastic and Adversarial Bandits
- Blog: Optimal Arms Identification with Knapsacks
- Blog: Best-of-Three-Worlds Linear Bandit Algorithm with Variance-Adaptive Regret Bounds
- Blog: Combinatorial Partial Monitoring Game with Linear Feedback and Its Applications
- Blog: Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm
- Blog: Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms
- Blog: Asymptotically Optimal Information-Directed Sampling
- Blog: The Mean-Squared Error of Double Q-Learning
- Blog: Multi-Reward Best Policy Identification
- Blog: Beyond the Policy Gradient Theorem for Efficient Policy Updates in Actor-Critic Algorithms
- Blog: Minding Motivation: The Effect of Intrinsic Motivation on Agent Behaviors
- Blog: Top Two Algorithms Revisited
- Blog: Unimodal Bandits: Regret Lower Bounds and Optimal Algorithms
- Blog: Breaking the $\log(1/\Delta_2)$ Barrier: Better Batched Best Arm Identification with Adaptive Grids
- Blog: Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel-Young Loss Perspective and Gap-Dependent Regret Analysis
- Blog: Adaptive Learning of Uncontrolled Restless Bandits with Logarithmic Regret
- Blog: Pure Exploration in Bandits with Linear Constraints
- Blog: Tsallis-INF: An Optimal Algorithm for Stochastic and Adversarial Bandits
- Blog: Asymptotically Optimal Information-Directed Sampling
- Blog: Testing stationarity and change point detection in reinforcement learning
- Blog: An Algorithm for Stochastic and Adversarial Bandits with Switching Costs
- Blog: Bandits with Knapsacks beyond the Worst Case
Showing 60 of 69 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_unique_optimal_action_assumption_b2bbdcbe,
title = {unique optimal action assumption},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unique-optimal-action-assumption/rdr_b2bbdcbe47954be3a2b620f2690b2c84},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-22},
}This exact version (version 2, frozen text):
@misc{lacuna_unique_optimal_action_assumption_b2bbdcbe_v2,
title = {unique optimal action assumption},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/unique-optimal-action-assumption/rdr_b2bbdcbe47954be3a2b620f2690b2c84/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-22},
}