No article text was recorded for this version.
mixing time dependency (parameter-free reinforcement learning)
Version 1 of 126 papers35 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
- Blog: An Out-of-Shelf Multi-Level Monte Carlo Approach for Average-Reward Reinforcement Learning
- Blog: Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
- Blog: Constrained Reinforcement Learning with Average Reward Objective: Model-Based and Model-Free Algorithms
- Blog: Optimal Sample Complexity for Average Reward Markov Decision Processes
- Blog: Feasible Q-Learning for Average Reward Reinforcement Learning
- Blog: Order-Optimal Regret with Novel Policy Gradient Approaches in Infinite-Horizon Average Reward MDPs
- Blog: Experts in a Markov Decision Process
- Blog: Towards Global Optimality for Practical Average Reward Reinforcement Learning without Mixing Time Oracles
- Blog: Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints
- Blog: Learning Unknown Markov Decision Processes: A Thompson Sampling Approach
- Blog: Unknown mixing times in apprenticeship and reinforcement learning
- Blog: Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
- Blog: Learning to Coordinate Efficiently: A Model-based Approach
- Blog: Near-Optimal Sample Complexity for MDPs via Anchoring
- Blog: Improved High-Probability Bounds for the Temporal Difference Learning Algorithm via Exponential Stability
- Blog: Nearly Minimax Optimal Regret for Learning Linear Mixture Stochastic Shortest Path
- Blog: Beyond Exponentially Fast Mixing in Average-Reward Reinforcement Learning via Multi-Level Monte Carlo Actor-Critic
- Blog: Primal-Dual Stochastic Mirror Descent for MDPs
- Blog: Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning
- Blog: Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
- Blog: Federated TD Learning over Finite-Rate Erasure Channels: Linear Speedup under Markovian Sampling
- Blog: Learning Infinite-horizon Average-reward Markov Decision Process with Constraints
- Blog: Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes
- Blog: A Simple Finite-Time Analysis of TD Learning with Linear Function Approximation
- Blog: Towards Parameter-Free Temporal Difference Learning
History & citation
Current · Permanent link
- This direction split from Reinforcement Learning Without Mixing Time Oracles (77% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_mixing_time_dependency_parameter_free_re_01017e1f,
title = {mixing time dependency (parameter-free reinforcement learning)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/mixing-time-dependency-parameter-free-reinforcement-learning/rdr_01017e1f9b904d4cb502da5e52171da9},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-21},
}This exact version (version 1, frozen text):
@misc{lacuna_mixing_time_dependency_parameter_free_re_01017e1f_v1,
title = {mixing time dependency (parameter-free reinforcement learning)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/mixing-time-dependency-parameter-free-reinforcement-learning/rdr_01017e1f9b904d4cb502da5e52171da9/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-21},
}