mlsanityData to 14 Oct 2026

Curricula for Learning Robust Policies with Factored State Representations in Changing Environments

arXiv 2409.09169 ↗First posted 13 Sep 2024cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

Robust policies enable reinforcement learning agents to effectively adapt to and operate in unpredictable, dynamic, and ever-changing real-world environments. Factored representations, which break down complex state and action spaces into distinct components, can improve generalization and sample efficiency in policy learning. In this paper, we explore how the curriculum of an agent using a factored state representation affects the robustness of the learned policy. We experimentally demonstrate three simple curricula, such as varying only the variable of highest regret between episodes, that can significantly enhance policy robustness, offering practical insights for reinforcement learning in complex environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 32 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

19 of 32 references.

References · 19

  1. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  2. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  3. 2020Curriculum Learning for Reinforcement Learning Domains: A Framework and Surveycited by 373
  4. 2020A Brief Review of Domain Adaptationcited by 288
  5. 2020Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Designcited by 275
  6. 2020Weakly-Supervised Disentanglement Without Compromisescited by 239
  7. 2018A Study on Overfitting in Deep Reinforcement Learningcited by 174
  8. 2022Evolving Curricula with Regret-Based Environment Designcited by 173
  9. 2018Learning Factorized Multimodal Representationscited by 171
  10. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  11. 2018Generalization and Regularization in DQNcited by 118
  12. 2013Deep Learning of Representations: Looking Forwardcited by 84
7 more
  1. 2024Robust agents learn causal world modelscited by 81
  2. 2018Evaluating Reinforcement Learning Algorithms in Observational Health Settingscited by 60
  3. 2022Factored Adaptation for Non-Stationary Reinforcement Learningcited by 30
  4. 2022A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learningcited by 15
  5. 2018Learning Factorized Representations for Open-set Domain Adaptationcited by 13
  6. 2017Independently Controllable Factorscited by 12
  7. 2022Robust Reinforcement Learning via Genetic Curriculumcited by 10

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Safety Representations for Safer Policy Learning
  2. 2023Reward-Free Curricula for Training Robust World Models
  3. 2024Safe and Robust Reinforcement Learning: Principles and Practice
  4. 2025Distributionally Robust Self Paced Curriculum Reinforcement Learning
  5. 2025State Entropy Regularization for Robust Reinforcement Learning
  6. 2024Inferring Behavior-Specific Context Improves Zero-Shot Generalization in Reinforcement Learning
  7. 2023Harnessing Discrete Representations For Continual Reinforcement Learning
  8. 2024An Investigation of Offline Reinforcement Learning in Factorisable Action Spaces