# A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning

arXiv: https://arxiv.org/abs/1902.00843 · HTML: https://mlsanity.com/paper/1902.00843/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Feb 2019.

## Built on by (most cited first, 18 of 18)

- [Human-Timescale Adaptation in an Open-Ended Task Space](https://mlsanity.com/paper/2301.07608/) (2023)
- [A Survey of Exploration Methods in Reinforcement Learning](https://mlsanity.com/paper/2109.00157/) (2021)
- [Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey](https://mlsanity.com/paper/2110.01411/) (2021)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [A Survey of Continual Reinforcement Learning](https://mlsanity.com/paper/2506.21872/) (2025)
- [Provably Efficient Multi-Task Reinforcement Learning with Model Transfer](https://mlsanity.com/paper/2107.08622/) (2021)
- [Learning an Explicit Hyperparameter Prediction Function Conditioned on Tasks](https://mlsanity.com/paper/2107.02378/) (2021)
- [Automated Reinforcement Learning: An Overview](https://mlsanity.com/paper/2201.05000/) (2022)
- [Reactive Exploration to Cope with Non-Stationarity in Lifelong Reinforcement Learning](https://mlsanity.com/paper/2207.05742/) (2022)
- [A Survey Analyzing Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/2401.02349/) (2024)
- [Continual Reinforcement Learning by Planning with Online World Models](https://mlsanity.com/paper/2507.09177/) (2025)
- [Meta Reinforcement Learning with Finite Training Tasks -- a Density Estimation Approach](https://mlsanity.com/paper/2206.10716/) (2022)
- [Lifelong Reinforcement Learning with Temporal Logic Formulas and Reward Machines](https://mlsanity.com/paper/2111.09475/) (2021)
- [Behavior Self-Organization Supports Task Inference for Continual Robot Learning](https://mlsanity.com/paper/2107.04533/) (2021)
- [MOORL: A Framework for Integrating Offline-Online Reinforcement Learning](https://mlsanity.com/paper/2506.09574/) (2025)
- [Reinforcement Teaching](https://mlsanity.com/paper/2204.11897/) (2022)
- [Knowing the Past to Predict the Future: Reinforcement Virtual Learning](https://mlsanity.com/paper/2211.01266/) (2022)
- [Stepsize Learning for Policy Gradient Methods in Contextual Markov Decision Processes](https://mlsanity.com/paper/2306.07741/) (2023)

## Abstract (arXiv)

In this paper we consider the problem of how a reinforcement learning agent that is tasked with solving a sequence of reinforcement learning problems (a sequence of Markov decision processes) can use knowledge acquired early in its lifetime to improve its ability to solve new problems. We argue that previous experience with similar problems can provide an agent with information about how it should explore when facing a new but related problem. We show that the search for an optimal exploration strategy can be formulated as a reinforcement learning problem itself and demonstrate that such strategy can leverage patterns found in the structure of related problems. We conclude with experiments that show the benefits of optimizing an exploration strategy using our proposed approach.