mlsanityData to 14 Oct 2026

Dynamics-aware Embeddings

arXiv 1908.09357 ↗First posted 25 Aug 2019cs.LG cs.AI stat.MLcited by 34

Not on the map. Why?

Abstract (arXiv)

In this paper we consider self-supervised representation learning to improve sample efficiency in reinforcement learning (RL). We propose a forward prediction objective for simultaneously learning embeddings of states and action sequences. These embeddings capture the structure of the environment's dynamics, enabling efficient policy learning. We demonstrate that our action embeddings alone improve the sample efficiency and peak performance of model-free RL on control from low-dimensional states. By combining state and action embeddings, we achieve efficient learning of high-quality policies on goal-conditioned continuous control from pixel observations in only 1-2 million environment steps.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 5; 2023: 11; 2024: 4; 2025: 1; 2026: 2.

34 papers.

Sort:

By area:

  1. 2021Demonstration-Guided Reinforcement Learning with Learned Skillscited by 76
  2. 2023For SALE: State-Action Representation Learning for Deep Reinforcement Learningcited by 75
  3. 2021Accelerating Robotic Reinforcement Learning via Parameterized Action Primitivescited by 65
  4. 2023PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Playcited by 50
  5. 2024HRP: Human Affordances for Robotic Pre-Trainingcited by 44
  6. 2024DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Controlcited by 44
  7. 2023An Unbiased Look at Datasets for Visuo-Motor Pre-Trainingcited by 42
  8. 2021Hierarchical Skills for Efficient Explorationcited by 38
  9. 2021HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representationcited by 35
  10. 2021LASER: Learning a Latent Action Space for Efficient Reinforcement Learningcited by 32
  11. 2023Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitationcited by 31
  12. 2021JueWu-MC: Playing Minecraft with Sample-efficient Hierarchical Reinforcement Learningcited by 28
22 more
  1. 2022Continuous MDP Homomorphisms and Homomorphic Policy Gradientcited by 27
  2. 2024Cross-Domain Policy Adaptation by Capturing Representation Mismatchcited by 25
  3. 2022Unsupervised Representation Learning in Deep Reinforcement Learning: A Reviewcited by 18
  4. 2021Hierarchical Neural Dynamic Policiescited by 17
  5. 2021Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learningcited by 14
  6. 2022One After Another: Learning Incremental Skills for a Changing Worldcited by 10
  7. 2023Policy Gradient Methods in the Presence of Symmetries and State Abstractionscited by 9
  8. 2023Learning minimal representations of stochastic processes with variational autoencoderscited by 7
  9. 2022SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Explorationcited by 6
  10. 2023Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domainscited by 6
  11. 2021Physical Reasoning Using Dynamics-Aware Modelscited by 4
  12. 2023Dynamic Neighborhood Construction for Structured Large Discrete Action Spacescited by 4
  13. 2022Leveraging Demonstrations with Latent Space Priorscited by 3
  14. 2025Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Informationcited by 2
  15. 2021A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settingscited by 1
  16. 2021Learning Routines for Effective Off-Policy Reinforcement Learningcited by 0
  17. 2023Learning Embeddings for Sequential Tasks Using Population of Agentscited by 0
  18. 2023DCT: Dual Channel Training of Action Embeddings for Reinforcement Learning with Large Discrete Action Spacescited by 0
  19. 2023A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Controlcited by 0
  20. 2024ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectoriescited by 0
  21. 2026Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spacescited by 0
  22. 2026DynaWM: Dynamics-Aware Distillation with World Model and Momentum Targets for Smooth Locomotion over Continuous Stairscited by 0