# MetaCURL: Non-stationary Concave Utility Reinforcement Learning

arXiv: https://arxiv.org/abs/2405.19807 · HTML: https://mlsanity.com/paper/2405.19807/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 30 of its 49 references that are in the map.
- First posted on arXiv 30 May 2024.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 30 of 30)

- [Provably Efficient Maximum Entropy Exploration](https://mlsanity.com/paper/1812.02690/) (2018)
- [A Divergence Minimization Perspective on Imitation Learning Methods](https://mlsanity.com/paper/1911.02256/) (2019)
- [Variational Policy Gradient Method for Reinforcement Learning with General Utilities](https://mlsanity.com/paper/2007.02151/) (2020)
- [Strongly Adaptive Online Learning](https://mlsanity.com/paper/1502.07073/) (2015)
- [Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approach](https://mlsanity.com/paper/2102.05406/) (2021)
- [Learning Adversarial MDPs with Bandit Feedback and Unknown Transition](https://mlsanity.com/paper/1912.01192/) (2019)
- [Reward is enough for convex MDPs](https://mlsanity.com/paper/2106.00661/) (2021)
- [Online Convex Optimization in Adversarial Markov Decision Processes](https://mlsanity.com/paper/1905.07773/) (2019)
- [Optimistic Policy Optimization with Bandit Feedback](https://mlsanity.com/paper/2002.08243/) (2020)
- [Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism](https://mlsanity.com/paper/2006.14389/) (2020)
- [On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method](https://mlsanity.com/paper/2102.08607/) (2021)
- [Concave Utility Reinforcement Learning: the Mean-Field Game Viewpoint](https://mlsanity.com/paper/2106.03787/) (2021)
- [Improved Strongly Adaptive Online Learning using Coin Betting](https://mlsanity.com/paper/1610.04578/) (2016)
- [Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition](https://mlsanity.com/paper/2006.05606/) (2020)
- [A Model Selection Approach for Corruption Robust Reinforcement Learning](https://mlsanity.com/paper/2110.03580/) (2021)
- [Dynamic Regret of Policy Optimization in Non-stationary Environments](https://mlsanity.com/paper/2007.00148/) (2020)
- [Variational Regret Bounds for Reinforcement Learning](https://mlsanity.com/paper/1905.05857/) (2019)
- [A Kernel-Based Approach to Non-Stationary Reinforcement Learning in Metric Spaces](https://mlsanity.com/paper/2007.05078/) (2020)
- [A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions](https://mlsanity.com/paper/1805.10066/) (2018)
- [Robust Policy Gradient against Strong Data Corruption](https://mlsanity.com/paper/2102.05800/) (2021)
- [Minimax Regret for Stochastic Shortest Path](https://mlsanity.com/paper/2103.13056/) (2021)
- [Stochastic Shortest Path with Adversarially Changing Costs](https://mlsanity.com/paper/2006.11561/) (2020)
- [Improved Corruption Robust Algorithms for Episodic Reinforcement Learning](https://mlsanity.com/paper/2102.06875/) (2021)
- [Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space](https://mlsanity.com/paper/2306.01854/) (2023)
- [Apprenticeship Learning via Frank-Wolfe](https://mlsanity.com/paper/1911.01679/) (2019)
- [No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions](https://mlsanity.com/paper/2305.17380/) (2023)
- [High-Probability Risk Bounds via Sequential Predictors](https://mlsanity.com/paper/2308.07588/) (2023)
- [Non-stationary Online Regression](https://mlsanity.com/paper/2011.06957/) (2020)
- [Improved Policy Optimization for Online Imitation Learning](https://mlsanity.com/paper/2208.00088/) (2022)
- [Generalized conditional gradient and learning in potential mean field games](https://mlsanity.com/paper/2209.12772/) (2022)

## Built on by (most cited first, 4 of 4)

- [Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2410.16600/) (2024)
- [Online Learning of Whittle Indices for Restless Bandits with Non-Stationary Transition Kernels](https://mlsanity.com/paper/2506.18186/) (2025)
- [Convex Markov Games and Beyond: New Proof of Existence, Characterization and Learning Algorithms for Nash Equilibria](https://mlsanity.com/paper/2602.12181/) (2026)
- [Global Optimality for Constrained Exploration via Penalty Regularization](https://mlsanity.com/paper/2604.28144/) (2026)

## Abstract (arXiv)

We explore online learning in episodic loop-free Markov decision processes on non-stationary environments (changing losses and probability transitions). Our focus is on the Concave Utility Reinforcement Learning problem (CURL), an extension of classical RL for handling convex performance criteria in state-action distributions induced by agent policies. While various machine learning problems can be written as CURL, its non-linearity invalidates traditional Bellman equations. Despite recent solutions to classical CURL, none address non-stationary MDPs. This paper introduces MetaCURL, the first CURL algorithm for non-stationary MDPs. It employs a meta-algorithm running multiple black-box algorithms instances over different intervals, aggregating outputs via a sleeping expert framework. The key hurdle is partial information due to MDP uncertainty. Under partial information on the probability transitions (uncertainty and non-stationarity coming only from external noise, independent of agent state-action pairs), we achieve optimal dynamic regret without prior knowledge of MDP changes. Unlike approaches for RL, MetaCURL handles full adversarial losses, not just stochastic ones. We believe our approach for managing non-stationarity with experts can be of interest to the RL community.