No article text was recorded for this version.
dual-sided pessimism
Version 1 of 140 papers48 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Online Reinforcement Learning in Stochastic Games
- Blog: Provable Self-Play Algorithms for Competitive Reinforcement Learning
- Blog: Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
- Blog: Pessimistic Minimax Value Iteration: Provably Efficient Equilibrium Learning from Offline Datasets
- Blog: When are Offline Two-Player Zero-Sum Markov Games Solvable?
- Blog: Can Reinforcement Learning Find Stackelberg-Nash Equilibria in General-Sum Markov Games with Myopically Rational Followers?
- Blog: Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium
- Blog: Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret
- Blog: Learning to Play Sequential Games versus Unknown Opponents
- Blog: A Novel Individually Rational Objective In Multi-Agent Multi-Armed Bandits: Algorithms and Regret Bounds
- Blog: Recherche heuristique pour jeux stochastiques (à somme nulle)
- Blog: Gap-Dependent Bounds for Two-Player Markov Games
- Blog: Online Learning in Unknown Markov Games
- Blog: Matrix games with bandit feedback
- Blog: Strategically efficient exploration in competitive multi-agent reinforcement learning
- Blog: Gamification of Pure Exploration for Linear Bandits
- Blog: Near-Optimal Reinforcement Learning with Self-Play
- Blog: Online Learning in Unknown Markov Games
- Blog: Towards General Function Approximation in Zero-Sum Markov Games
- Blog: Reinforcement Learning under Threats
- Blog: Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
- Blog: Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
- Blog: Finite-sample guarantees for Nash Q-learning with linear function approximation
- Blog: Alpha-Beta Pruning for Games with Simultaneous Moves
- Blog: Learning in Markov games: Can we exploit a general-sum opponent?
- Blog: Opponent-Model Search in Games with Incomplete Information
- Blog: Online Multiagent Learning against Memory Bounded Adversaries
- Blog: Almost Optimal Algorithms for Two-player Zero-Sum Linear Mixture Markov Games
- Blog: Algorithms for Finding Approximate Formations in Games
- Blog: A Framework for Finding Local Saddle Points in Two-Player Zero-Sum Black-Box Games
- Blog: Optimistic Thompson Sampling for No-Regret Learning in Unknown Games
- Blog: Heuristic Search Value Iteration for Zero-Sum Stochastic Games
- Blog: Differentially Private Reinforcement Learning with Self-Play
- Blog: Exploiting Opponents Under Utility Constraints in Sequential Games
- Blog: Representation Learning for Low-rank General-sum Markov Games
- Blog: The Power of Exploiter: Provable Multi-Agent RL in Large State Spaces
- Blog: No-regret Sample-efficient Bayesian Optimization for Finding Nash Equilibria with Unknown Utilities
- Blog: Policy-Regret Minimization in Markov Games with Function Approximation
- Blog: Exploration Analysis in Finite-Horizon Turn-based Stochastic Games
- Blog: Finding and Certifying (Near-)Optimal Strategies in Black-Box Extensive-Form Games
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_dual_sided_pessimism_48793840,
title = {dual-sided pessimism},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/dual-sided-pessimism/rdr_4879384072a048ccb36f7a3cc7c3a9db},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_dual_sided_pessimism_48793840_v1,
title = {dual-sided pessimism},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/dual-sided-pessimism/rdr_4879384072a048ccb36f7a3cc7c3a9db/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}