mlsanityData to 14 Oct 2026

PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning

arXiv 2508.02159 ↗First posted 4 Aug 2025cs.LGcited by 7

On the map: World models → Latent dynamics models and model-based RL

also in 1 more
Abstract (arXiv)

Partial observability presents a significant challenge for Safe Reinforcement Learning (Safe RL), as it impedes the identification of potential risks and rewards. Leveraging specific types of privileged information during training to mitigate the effects of partial observability has yielded notable empirical successes. In this paper, we propose Asymmetric Constrained Partially Observable Markov Decision Processes (ACPOMDPs) to theoretically examine the advantages of incorporating privileged information in Safe RL. Building upon ACPOMDPs, we propose the Privileged Information Guided Dreamer (PIGDreamer), a model-based RL approach that leverages privileged information to enhance the agent's safety and performance through privileged representation alignment and an asymmetric actor-critic structure. Our empirical results demonstrate that PIGDreamer significantly outperforms existing Safe RL methods. Furthermore, compared to alternative privileged RL methods, our approach exhibits enhanced performance, robustness, and efficiency. Codes are available at: https://github.com/hggforget/PIGDreamer.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Latent dynamics models and model-based RL, one of 11 directions in World models. Builds on 23 of its 42 references that are in the map. First posted on arXiv 4 Aug 2025.

Builds on

23 of 42 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023SafeDreamer: Safe Reinforcement Learning with World Models14 Jul
  2. 2023Mastering Diverse Domains through World Models10 Jan
  3. 2019Dream to Control: Learning Behaviors by Latent Imagination3 Dec

Other references · 20

  1. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  2. 2017Constrained Policy Optimizationcited by 983
  3. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  4. 2018Learning Dexterous In-Hand Manipulationcited by 687
  5. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 366
  6. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 238
  7. 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 231
  8. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  9. 2022Safe Reinforcement Learning by Imagining the Near Futurecited by 67
  10. 2020Sample-Efficient Reinforcement Learning of Undercomplete POMDPscited by 66
  11. 2020Suphx: Mastering Mahjong with Deep Reinforcement Learningcited by 58
  12. 2022Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithmcited by 29
8 more
  1. 2021Unbiased Asymmetric Reinforcement Learning under Partial Observabilitycited by 25
  2. 2023TWIST: Teacher-Student World Model Distillation for Efficient Sim-to-Real Transfercited by 19
  3. 2021Safe Continuous Control with Constrained Model-Based Policy Optimizationcited by 17
  4. 2023GUARD: A Safe Reinforcement Learning Benchmarkcited by 13
  5. 2024Provable Partially Observable Reinforcement Learning with Privileged Informationcited by 13
  6. 2022Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representationcited by 11
  7. 2023The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Modelscited by 9
  8. 2021The Augmented Lagrangian Method Can Approximately Solve Convex Optimization with Least Constraint Violationcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 5.

7 papers.

  1. 2026MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mindcited by 3
  2. 2025Unifying Agent Interaction and World Information for Multi-agent Coordinationcited by 2
  3. 2025Driving Beyond Privilege: Distilling Dense-Reward Knowledge into Sparse-Reward Policiescited by 2
  4. 2026Confounding Robust Continuous Control via Automatic Reward Shapingcited by 2
  5. 2026Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learningcited by 2
  6. 2026JEPA-x: Cross-Predictive Physics Grounding for Forecastable Latent Dynamicscited by 1
  7. 2026Belief-State RWKV for Reinforcement Learning under Partial Observabilitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Compositional shield synthesis for safe reinforcement learning in partial observability
  2. 2025PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies
  3. 2025Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
  4. 2026PriPG-RL: Privileged Planner-Guided Reinforcement Learning for Partially Observable Systems with Anytime-Feasible MPC
  5. 2026Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance
  6. 2025A Survey of Safe Reinforcement Learning and Constrained MDPs: A Technical Survey on Single-Agent and Multi-Agent Safety
  7. 2025To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable Reinforcement Learning
  8. 2025Guided Policy Optimization under Partial Observability