# Time-Constrained Robust MDPs

arXiv: https://arxiv.org/abs/2406.08395 · HTML: https://mlsanity.com/paper/2406.08395/

## Key facts

- Cited by 2 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 19 of its 33 references that are in the map.
- First posted on arXiv 12 Jun 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, 19 of 19)

- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Solving Rubik's Cube with a Robot Hand](https://mlsanity.com/paper/1910.07113/) (2019)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations](https://mlsanity.com/paper/2003.08938/) (2020)
- [Action Robust Reinforcement Learning and Applications in Continuous Control](https://mlsanity.com/paper/1901.09184/) (2019)
- [Active Domain Randomization](https://mlsanity.com/paper/1904.04762/) (2019)
- [Robust Reinforcement Learning on State Observations with Learned Optimal Adversary](https://mlsanity.com/paper/2101.08452/) (2021)
- [Robust Reinforcement Learning using Adversarial Populations](https://mlsanity.com/paper/2008.01825/) (2020)
- [Wasserstein Robust Reinforcement Learning](https://mlsanity.com/paper/1907.13196/) (2019)
- [Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version](https://mlsanity.com/paper/1904.10090/) (2019)
- [A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions](https://mlsanity.com/paper/1805.10066/) (2018)
- [Robust Markov Decision Process: Beyond Rectangularity](https://mlsanity.com/paper/1811.00215/) (2018)
- [Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions](https://mlsanity.com/paper/1303.3055/) (2013)
- [Policy Gradient Algorithms for Robust MDPs with Non-Rectangular Uncertainty Sets](https://mlsanity.com/paper/2305.19004/) (2023)
- [Max-Min Off-Policy Actor-Critic Method Focusing on Worst-Case Robustness to Model Misspecification](https://mlsanity.com/paper/2211.03413/) (2022)
- [Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation](https://mlsanity.com/paper/1911.12976/) (2019)
- [Robust Reinforcement Learning with Distributional Risk-averse formulation](https://mlsanity.com/paper/2206.06841/) (2022)
- [Non-Stationary Reinforcement Learning: The Blessing of (More) Optimism](https://mlsanity.com/paper/1906.02922/) (2019)

## Built on by (most cited first, 2 of 2)

- [Linear Mixture Distributionally Robust Markov Decision Processes](https://mlsanity.com/paper/2505.18044/) (2025)
- [Reward-Preserving Attacks For Robust Reinforcement Learning](https://mlsanity.com/paper/2601.07118/) (2026)

## Abstract (arXiv)

Robust reinforcement learning is essential for deploying reinforcement learning algorithms in real-world scenarios where environmental uncertainty predominates. Traditional robust reinforcement learning often depends on rectangularity assumptions, where adverse probability measures of outcome states are assumed to be independent across different states and actions. This assumption, rarely fulfilled in practice, leads to overly conservative policies. To address this problem, we introduce a new time-constrained robust MDP (TC-RMDP) formulation that considers multifactorial, correlated, and time-dependent disturbances, thus more accurately reflecting real-world dynamics. This formulation goes beyond the conventional rectangularity paradigm, offering new perspectives and expanding the analytical framework for robust RL. We propose three distinct algorithms, each using varying levels of environmental information, and evaluate them extensively on continuous control benchmarks. Our results demonstrate that these algorithms yield an efficient tradeoff between performance and robustness, outperforming traditional deep robust RL methods in time-constrained environments while preserving robustness in classical benchmarks. This study revisits the prevailing assumptions in robust RL and opens new avenues for developing more practical and realistic RL applications.