mlsanityData to 14 Oct 2026

DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training

arXiv 2305.12127 ↗First posted 20 May 2023cs.RO cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

In this work, we propose algorithms and methods that enable learning dexterous object manipulation using simulated one- or two-armed robots equipped with multi-fingered hand end-effectors. Using a parallel GPU-accelerated physics simulator (Isaac Gym), we implement challenging tasks for these robots, including regrasping, grasp-and-throw, and object reorientation. To solve these problems we introduce a decentralized Population-Based Training (PBT) algorithm that allows us to massively amplify the exploration capabilities of deep reinforcement learning. We find that this method significantly outperforms regular end-to-end learning and is able to discover robust control policies in challenging tasks. Video demonstrations of learned behaviors and the code can be found at https://sites.google.com/view/dexpbt

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 31 of its 43 references that are in the map. First posted on arXiv 20 May 2023.

Builds on

31 of 43 references.

References · 31

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  3. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  4. 2015End-to-End Training of Deep Visuomotor Policiescited by 875
  5. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  6. 2019Solving Rubik's Cube with a Robot Handcited by 734
  7. 2018Learning Dexterous In-Hand Manipulationcited by 687
  8. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  9. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  10. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 407
  11. 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
  12. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
19 more
  1. 2017Population Based Training of Neural Networkscited by 367
  2. 2022Masked Visual Pre-training for Motor Controlcited by 248
  3. 2018Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experiencecited by 217
  4. 2020Rearrangement: A Challenge for Embodied AIcited by 155
  5. 2022DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Realitycited by 149
  6. 2022Towards Human-Level Bimanual Dexterous Manipulation with Reinforcement Learningcited by 119
  7. 2021Reset-Free Reinforcement Learning via Multi-Task Learning: Learning Dexterous Manipulation Behaviors without Human Interventioncited by 95
  8. 2020Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learningcited by 93
  9. 2021From Motor Control to Team Play in Simulated Humanoid Footballcited by 87
  10. 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulationcited by 85
  11. 2021Autonomous Drone Racing with Deep Reinforcement Learningcited by 60
  12. 2022Factory: Fast Contact for Robotic Assemblycited by 54
  13. 2019Sim-to-(Multi)-Real: Transfer of Low-Level Robust Control Policies to Multiple Quadrotorscited by 45
  14. 2021Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFingercited by 38
  15. 2022Bayesian Generational Population-Based Trainingcited by 20
  16. 2021Decentralized Control of Quadrotor Swarms with End-to-end Deep Reinforcement Learningcited by 19
  17. 2021Geometric Fabrics: Generalizing Classical Mechanics to Capture the Physics of Behaviorcited by 19
  18. 2021RMP2: A Structured Composable Policy Class for Robot Learningcited by 8
  19. 2022Fast Population-Based Reinforcement Learning on a Single Machinecited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 6; 2025: 9; 2026: 10.

29 papers.

Sort:

By area:

  1. 2025Robust Autonomy Emerges from Self-Playcited by 67
  2. 2025Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoidscited by 48
  3. 2024EfficientZero V2: Mastering Discrete and Continuous Control with Limited Datacited by 40
  4. 2024Hand-Object Interaction Pretraining from Videoscited by 39
  5. 2023Dynamic Handover: Throw and Catch with Bimanual Handscited by 35
  6. 2024SAPG: Split and Aggregate Policy Gradientscited by 21
  7. 2026SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulationcited by 15
  8. 2024DexTouch: Learning to Seek and Manipulate Objects with Tactile Dexteritycited by 12
  9. 2024DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robotscited by 11
  10. 2023Estimator-Coupled Reinforcement Learning for Robust Purely Tactile In-Hand Manipulationcited by 9
  11. 2023DexCatch: Learning to Catch Arbitrary Objects with Dexterous Handscited by 8
  12. 2023DexDLO: Learning Goal-Conditioned Dexterous Policy for Dynamic Manipulation of Deformable Linear Objectscited by 4
17 more
  1. 2025Evolutionary Policy Optimizationcited by 4
  2. 2026On the Role of Computation in Reinforcement Learningcited by 3
  3. 2025Learning Long-Horizon Robot Manipulation Skills via Privileged Actioncited by 2
  4. 2026ADEPT: Accelerating Dexterity via Pre-Training and Post-Training using Reinforcement Learningcited by 2
  5. 2024Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulationcited by 1
  6. 2025EvoRL: A GPU-accelerated Framework for Evolutionary Reinforcement Learningcited by 1
  7. 2025Learning Dexterous Bimanual Catch Skills through Adversarial-Cooperative Heterogeneous-Agent Reinforcement Learningcited by 1
  8. 2025Prompt-responsive Object Retrieval with Memory-augmented Student-Teacher Learningcited by 1
  9. 2025Interactive Shaping of Granular Media Using Reinforcement Learningcited by 1
  10. 2026Benchmarking Action Spaces in Reinforcement Learning for Vision-based Robotic Manipulationcited by 1
  11. 2025Parental Guidance: Efficient Lifelong Learning through Evolutionary Distillationcited by 0
  12. 2026Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learningcited by 0
  13. 2026ContactExplorer: Contact Coverage-Guided Exploration for General-Purpose Dexterous Manipulationcited by 0
  14. 2026Pre-training Visual Dexterity in Simulationcited by 0
  15. 2026Non-Prehensile Throwing: A Reinforcement Learning Perspectivecited by 0
  16. 2026Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speedscited by 0
  17. 2026A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Controlcited by 0