mlsanityData to 7 Oct 2026

Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes

arXiv 2408.03539 ↗First posted 7 Aug 2024cs.RO cs.LGcited by 153

Not on the map. Why?

Cited by 21 in Offline RL and imitation learning from data, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Reinforcement learning (RL), particularly its combination with deep neural networks referred to as deep RL (DRL), has shown tremendous promise across a wide range of applications, suggesting its potential for enabling the development of sophisticated robotic behaviors. Robotics problems, however, pose fundamental difficulties for the application of RL, stemming from the complexity and cost of interacting with the physical world. This article provides a modern survey of DRL for robotics, with a particular focus on evaluating the real-world successes achieved with DRL in realizing several key robotic competencies. Our analysis aims to identify the key factors underlying those exciting successes, reveal underexplored areas, and provide an overall characterization of the status of DRL in robotics. We highlight several important avenues for future work, emphasizing the need for stable and sample-efficient real-world RL paradigms, holistic approaches for discovering and integrating various competencies to tackle complex long-horizon, open-world tasks, and principled development and evaluation procedures. This survey is designed to offer insights for both RL practitioners and roboticists toward harnessing RL's power to create generally capable real-world robotic systems.

Key facts. Cited by 153 papers in the map (data through 7 Oct 2026). Builds on 158 of its 201 references that are in the map. First posted on arXiv 7 Aug 2024.

Builds on

158 of 201 references.

References · 158

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,327
  3. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  4. 2017Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environmentscited by 1,013
  5. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  6. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  7. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  8. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  9. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  10. 2020AWAC: Accelerating Online Reinforcement Learning with Offline Datasetscited by 647
  11. 2018Learning Dexterous In-Hand Manipulationcited by 643
  12. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 494
38 more
  1. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  2. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  3. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  4. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
  5. 2019Learning agile and dynamic motor skills for legged robotscited by 402
  6. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Trainingcited by 384
  7. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  8. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
  9. 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
  10. 2019Reinforcement Learning in Healthcare: A Surveycited by 308
  11. 2017Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewardscited by 302
  12. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 299
  13. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 277
  14. 2018Learning to Drive in a Daycited by 266
  15. 2018Visual Reinforcement Learning with Imagined Goalscited by 248
  16. 2018Residual Reinforcement Learning for Robot Controlcited by 242
  17. 2016CAD2RL: Real Single-Image Flight without a Single Real Imagecited by 227
  18. 2018Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Controlcited by 220
  19. 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 203
  20. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 202
  21. 2021How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learnedcited by 201
  22. 2019Deep Dynamics Models for Learning Dexterous Manipulationcited by 200
  23. 2021Reinforcement learning based recommender systems: A surveycited by 187
  24. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 171
  25. 2018Learning by Playing - Solving Sparse Reward Tasks from Scratchcited by 164
  26. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 164
  27. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  28. 2019A Review of Robot Learning for Manipulation: Challenges, Representations, and Algorithmscited by 136
  29. 2022DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Realitycited by 136
  30. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 132
  31. 2023FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulationcited by 132
  32. 2022Legged Locomotion in Challenging Terrains using Egocentric Visioncited by 131
  33. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 129
  34. 2017Socially Aware Motion Planning with Deep Reinforcement Learningcited by 128
  35. 2021Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skillscited by 125
  36. 2018Sim-to-Real Reinforcement Learning for Deformable Object Manipulationcited by 124
  37. 2018Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learningcited by 121
  38. 2021Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotationcited by 117

50 most cited of 158 All 158 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 73; 2026: 67.

153 papers.

Sort:

By area:

  1. 2025VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learningcited by 166
  2. 2024Exploring the Adversarial Vulnerabilities of Vision-Language-Action Models in Roboticscited by 68
  3. 2024FLaRe: Achieving Masterful and Adaptive Robot Policies with Large-Scale Reinforcement Learning Fine-Tuningcited by 54
  4. 2025EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modelingcited by 29
  5. 2025Manual2Skill: Learning to Read Manuals and Acquire Robotic Skills for Furniture Assembly Using Vision-Language Modelscited by 13
  6. 2024Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learningcited by 9
  7. 2024SkiLD: Unsupervised Skill Discovery Guided by Factor Interactionscited by 9
  8. 2025medDreamer: Model-Based Reinforcement Learning with Latent Imagination on Complex EHRs for Clinical Decision Supportcited by 8
  9. 2025Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Datacited by 8
  10. 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environmentscited by 8
  11. 2026Why AI systems don't learn and what to do about it: Lessons on autonomous learning from cognitive sciencecited by 8
  12. 2025SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learningcited by 7
38 more
  1. 2025SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-Trainingcited by 7
  2. 2025Towards Robust Zero-Shot Reinforcement Learningcited by 7
  3. 2025Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learningcited by 7
  4. 2025SOMBRL: Scalable and Optimistic Model-Based RLcited by 7
  5. 2026ReWorld: Multi-Dimensional Reward Modeling for Embodied World Modelscited by 7
  6. 2025Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learningcited by 6
  7. 2025Text Reinforcement for Multimodal Time Series Forecastingcited by 6
  8. 2025Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learningcited by 6
  9. 2025Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learningcited by 6
  10. 2024Reinforcement Learning Within the Classical Robotics Stack: A Case Study in Robot Soccercited by 5
  11. 2025SafeMimic: Towards Safe and Autonomous Human-to-Robot Imitation for Mobile Manipulationcited by 5
  12. 2025Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulationcited by 5
  13. 2025TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distancecited by 5
  14. 2026Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directionscited by 5
  15. 2024Goal-Conditioned Data Augmentation for Offline Reinforcement Learningcited by 4
  16. 2025Optimistic critics can empower small actorscited by 4
  17. 2025MOORL: A Framework for Integrating Offline-Online Reinforcement Learningcited by 4
  18. 2025Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolutioncited by 4
  19. 2025AVERY: Intent-Driven Adaptive VLM Split Computing via Embodied Self-Awareness for Efficient Disaster Response Systemscited by 4
  20. 2025RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RLcited by 4
  21. 2024Explainable Concept Generation through Vision-Language Preference Learning for Understanding Neural Networks' Internal Representationscited by 3
  22. 2024A Survey on Reinforcement Learning Applications in SLAMcited by 3
  23. 2025New Evidence of the Two-Phase Learning Dynamics of Neural Networkscited by 3
  24. 2025EDEN: Entorhinal Driven Egocentric Navigation Toward Robotic Deploymentcited by 3
  25. 2025Improved Robustness of Deep Reinforcement Learning for Control of Time-Varying Systems by Bounded Extremum Seekingcited by 3
  26. 2025Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularizationcited by 3
  27. 2025Spectral Representation-based Reinforcement Learningcited by 3
  28. 2025ReinforceGen: Hybrid Skill Policies with Automated Data Generation and Reinforcement Learningcited by 3
  29. 2026Failing Forward: Adaptive Failure-Informed Learning for Vision-Language-Action Modelscited by 3
  30. 2026Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Drivingcited by 3
  31. 2024Offline-to-online Reinforcement Learning for Image-based Grasping with Scarce Demonstrationscited by 2
  32. 2024Learning to Look: Seeking Information for Decision Making via Policy Factorizationcited by 2
  33. 2025GraspCorrect: Robotic Grasp Correction via Vision-Language Model-Guided Feedbackcited by 2
  34. 2025Probabilistic Curriculum Learning for Goal-Based Reinforcement Learningcited by 2
  35. 2025Policy-Based Trajectory Clustering in Offline Reinforcement Learningcited by 2
  36. 2025Perspective on Utilizing Foundation Models for Laboratory Automation in Materials Researchcited by 2
  37. 2025Provably Efficient and Agile Randomized Q-Learningcited by 2
  38. 2025Off Policy Lyapunov Stability in Reinforcement Learningcited by 2

50 most cited of 153 All 153 (JSON)