mlsanityData to 7 Oct 2026

Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model

arXiv 1907.00953 ↗First posted 1 Jul 2019cs.LG cs.AI stat.MLcited by 228

Not on the map. Why?

Cited by 23 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn directly from image observations. However, these high-dimensional observation spaces present a number of challenges in practice, since the policy must now solve two problems: representation learning and task learning. In this work, we tackle these two problems separately, by explicitly learning latent representations that can accelerate reinforcement learning from images. We propose the stochastic latent actor-critic (SLAC) algorithm: a sample-efficient and high-performing RL algorithm for learning policies for complex continuous control tasks directly from high-dimensional image inputs. SLAC provides a novel and principled approach for unifying stochastic sequential models and RL into a single method, by learning a compact latent representation and then performing RL in the model's learned latent space. Our experimental evaluation demonstrates that our method outperforms both model-free and model-based alternatives in terms of final performance and sample efficiency, on a range of difficult image-based control tasks. Our code and videos of our results are available at our website.

Key facts. Cited by 228 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 2; 2021: 53; 2022: 60; 2023: 43; 2024: 29; 2025: 30; 2026: 11.

228 papers.

Sort:

By area:

  1. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 781
  2. 2021COMBO: Conservative Offline Model-Based Policy Optimizationcited by 365
  3. 2021Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learningcited by 359
  4. 2021Reinforcement Learning with Prototypical Representationscited by 179
  5. 2023Structured World Models from Human Videoscited by 144
  6. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 115
  7. 2020Offline Reinforcement Learning from Images with Latent Space Modelscited by 94
  8. 2021Learning by Watching: Physical Imitation of Manipulation Skills from Human Videoscited by 87
  9. 2023DREAMWALKER: Mental Planning for Continuous Vision-Language Navigationcited by 82
  10. 2022CACTI: A Framework for Scalable Multi-Task Multi-Scene Visual Imitation Learningcited by 70
  11. 2022Denoised MDPs: Learning World Models Better Than the World Itselfcited by 66
  12. 2022Saute RL: Almost Surely Safe Reinforcement Learning Using State Augmentationcited by 63
38 more
  1. 2023TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learningcited by 56
  2. 2024Bridging State and History Representations: Understanding Self-Predictive RLcited by 52
  3. 2023SafeDreamer: Safe Reinforcement Learning with World Modelscited by 50
  4. 2021Towards Robust Bisimulation Metric Learningcited by 49
  5. 2023DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimizationcited by 45
  6. 2022Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Modelcited by 44
  7. 2022Visuo-Tactile Transformers for Manipulationcited by 43
  8. 2021Learning Markov State Abstractions for Deep Reinforcement Learningcited by 42
  9. 2021Visual Adversarial Imitation Learning using Variational Modelscited by 42
  10. 2021PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learningcited by 41
  11. 2022AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoderscited by 41
  12. 2025Towards General-Purpose Model-Free Reinforcement Learningcited by 40
  13. 2022Mask-based Latent Reconstruction for Reinforcement Learningcited by 39
  14. 2025DynaGuide: Steering Diffusion Polices with Active Dynamic Guidancecited by 39
  15. 2022Learning to Accelerate Partial Differential Equations via Latent Global Evolutioncited by 38
  16. 2022Learning to Drive by Watching YouTube Videos: Action-Conditioned Contrastive Policy Pretrainingcited by 37
  17. 2023Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learningcited by 37
  18. 2021Return-Based Contrastive Representation Learning for Reinforcement Learningcited by 36
  19. 2022Stabilizing Off-Policy Deep Reinforcement Learning from Pixelscited by 32
  20. 2024AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agentscited by 32
  21. 2021DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneckcited by 31
  22. 2021Action-Sufficient State Representation Learning for Control with Structural Constraintscited by 31
  23. 2021Learning a State Representation and Navigation in Cluttered and Dynamic Environmentscited by 30
  24. 2021Robust Predictable Controlcited by 29
  25. 2023Self-Improving Robots: End-to-End Autonomous Visuomotor Reinforcement Learningcited by 29
  26. 2023Explicitly Minimizing the Blur Error of Variational Autoencoderscited by 29
  27. 2021Which Mutual-Information Representation Learning Objectives are Sufficient for Control?cited by 28
  28. 2022Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objectivecited by 28
  29. 2022INFOrmation Prioritization through EmPOWERment in Visual Model-Based RLcited by 27
  30. 2021Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoningcited by 25
  31. 2021Learning Representations for Pixel-based Control: What Matters and Why?cited by 24
  32. 2022Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?cited by 24
  33. 2022The Free Energy Principle for Perception and Action: A Deep Learning Perspectivecited by 24
  34. 2022Generalization with Lossy Affordances: Leveraging Broad Offline Data for Learning Visuomotor Taskscited by 24
  35. 2025ViPRA: Video Prediction for Robot Actionscited by 24
  36. 2022A Comprehensive Survey of Data Augmentation in Visual Reinforcement Learningcited by 23
  37. 2022Planning for Sample Efficient Imitation Learningcited by 20
  38. 2023Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Criticcited by 20

50 most cited of 228 All 228 (JSON)