Evo-RL: Iterative Robot Reinforcement Learning from Selective Experience
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
Existing real-world reinforcement learning methods improve robot policies by combining human corrections with autonomous rollouts. However, accumulated experience varies in its value for policy improvement, and even successful trajectories can contain inefficient or redundant behavior, motivating more selective experience reuse. To this end, we propose Evo-RL, an iterative reinforcement learning method that combines human interventions with advantage-guided experience selection. Evo-RL uses human corrections and experience with positive estimated advantages from successful trajectories to iteratively refine the policy. To support learning from these different experience sources, we introduce RW-RL-Dataset, which spans over 1,000 hours across four robot embodiments. On a real-world high-precision manipulation task, Evo-RL improves attempt success rate over RECAP by 30.46%. Our code, model checkpoints, and dataset are publicly available.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 20 of its 22 references that are in the map. First posted on arXiv 9 Oct 2026.
Builds on
20 of 22 references.
Closest ancestors · 1
Same direction, newest first
Other references · 19
- 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
- 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
- 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
- 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
- 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
- 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
- 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
- 2025π*0.6: a VLA That Learns From Experiencecited by 303
- 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 266
- 2025Real-Time Execution of Action Chunking Flow Policiescited by 216
- 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
- 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 175
7 more
- 2020Human-in-the-Loop Imitation Learning using Remote Teleoperationcited by 112
- 2024GRAPE: Generalizing Robot Policy via Preference Alignmentcited by 109
- 2021ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learningcited by 108
- 2026A Pragmatic VLA Foundation Modelcited by 103
- 2025Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignmentcited by 41
- 2023RLIF: Interactive Imitation Learning as Reinforcement Learningcited by 30
- 2026LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoningcited by 8
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
- 2024SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
- 2026OHP-RL: Online Human Preference as Guidance in Reinforcement Learning for Robot Manipulation
- 2026Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience
- 2025Real-world Reinforcement Learning from Suboptimal Interventions
- 2025SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning
- 2025Taxonomy and Trends in Reinforcement Learning for Robotics and Control Systems: A Structured Review
- 2024Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning