# Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation

arXiv: https://arxiv.org/abs/2512.23703 · HTML: https://mlsanity.com/paper/2512.23703/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 40 of its 65 references that are in the map.
- First posted on arXiv 29 Dec 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Deep reinforcement learning methods / [RL for robot locomotion and manipulation](https://mlsanity.com/deeprl/rl-for-robot-locomotion-and-manipulation/)

## Builds on (most cited first, 30 of 40)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [GR00T N1: An Open Foundation Model for Generalist Humanoid Robots](https://mlsanity.com/paper/2503.14734/) (2025)
- [Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success](https://mlsanity.com/paper/2502.19645/) (2025)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation](https://mlsanity.com/paper/2506.18088/) (2025)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems](https://mlsanity.com/paper/2503.06669/) (2025)
- [X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model](https://mlsanity.com/paper/2510.10274/) (2025)
- [LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training](https://mlsanity.com/paper/2509.23661/) (2025)
- [EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video](https://mlsanity.com/paper/2505.11709/) (2025)
- [VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning](https://mlsanity.com/paper/2505.18719/) (2025)
- [ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy](https://mlsanity.com/paper/2502.05450/) (2025)
- [SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning](https://mlsanity.com/paper/2509.09674/) (2025)
- [RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics](https://mlsanity.com/paper/2506.04308/) (2025)
- [What Can RL Bring to VLA Generalization? An Empirical Study](https://mlsanity.com/paper/2505.19789/) (2025)
- [ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning](https://mlsanity.com/paper/2505.22094/) (2025)
- [StreamingVLM: Real-Time Understanding for Infinite Video Streams](https://mlsanity.com/paper/2510.09608/) (2025)
- [RoboBrain 2.0 Technical Report](https://mlsanity.com/paper/2507.02029/) (2025)
- [Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer](https://mlsanity.com/paper/2510.03342/) (2025)
- [Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone](https://mlsanity.com/paper/2412.06685/) (2024)
- [A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning](https://mlsanity.com/paper/2509.15937/) (2025)
- [RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning](https://mlsanity.com/paper/2510.14830/) (2025)
- [TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization](https://mlsanity.com/paper/2506.08440/) (2025)
- [RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning](https://mlsanity.com/paper/2412.09858/) (2024)
- [ReinboT: Amplifying Robot Visual-Language Manipulation with Reinforcement Learning](https://mlsanity.com/paper/2505.07395/) (2025)

## Built on by (most cited first, 30 of 40)

- [Robometer: Scaling General-Purpose Robotic Reward Models via Trajectory Comparisons](https://mlsanity.com/paper/2603.02115/) (2026)
- [TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics](https://mlsanity.com/paper/2602.19313/) (2026)
- [RLDX-1 Technical Report](https://mlsanity.com/paper/2605.03269/) (2026)
- [PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2601.07060/) (2026)
- [Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models](https://mlsanity.com/paper/2603.16065/) (2026)
- [PRM-as-a-Judge: A Dense Evaluation Paradigm for Fine-Grained Robotic Auditing](https://mlsanity.com/paper/2603.21669/) (2026)
- [ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation](https://mlsanity.com/paper/2605.08774/) (2026)
- [ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents](https://mlsanity.com/paper/2604.10096/) (2026)
- [RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance](https://mlsanity.com/paper/2608.09853/) (2026)
- [From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation](https://mlsanity.com/paper/2603.15600/) (2026)
- [Progress Reward Modeling for Robotic Learning: A Comprehensive Survey](https://mlsanity.com/paper/2607.21655/) (2026)
- [Action-Sketcher: From Reasoning to Action via Visual Sketches for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2601.01618/) (2026)
- [Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation](https://mlsanity.com/paper/2603.05185/) (2026)
- [SAIL: Test-Time Scaling for In-Context Imitation Learning with VLM](https://mlsanity.com/paper/2603.08269/) (2026)
- [SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning](https://mlsanity.com/paper/2603.28730/) (2026)
- [VLA-FAIL: Efficient Task Failure Detection for Finetuned Vision-Language-Action Models](https://mlsanity.com/paper/2606.21386/) (2026)
- [RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation](https://mlsanity.com/paper/2606.22027/) (2026)
- [ELASTIC: Efficiently Learning to Adaptively Scale Test-Time Compute for Generative Control Policies](https://mlsanity.com/paper/2606.31132/) (2026)
- [PRM-as-a-Judge 1.5: A Toolkit for Robot Process Assessment](https://mlsanity.com/paper/2608.14284/) (2026)
- [RoDiF: Robust Direct Fine-Tuning of Diffusion Policies with Corrupted Human Feedback](https://mlsanity.com/paper/2602.00886/) (2026)
- [Dual-Granularity Contrastive Reward via Generated Episodic Guidance for Efficient Embodied RL](https://mlsanity.com/paper/2602.12636/) (2026)
- [SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation](https://mlsanity.com/paper/2606.10305/) (2026)
- [Latent Goal Prediction from Language for Model-Based Planning](https://mlsanity.com/paper/2606.20627/) (2026)
- [DenseReward: Dense Reward Learning via Failure Synthesis for Robotic Manipulation](https://mlsanity.com/paper/2607.13033/) (2026)
- [From Demonstrations to Rewards: Test-Time Prompt Optimization for VLM Reward Models](https://mlsanity.com/paper/2606.00083/) (2026)
- [StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement](https://mlsanity.com/paper/2606.00267/) (2026)
- [Learning Process Rewards via Success Visitation Matching for Efficient RL](https://mlsanity.com/paper/2606.23640/) (2026)
- [TACO: TActile World Model as a Self-COrrector for Scalable Robot Policy Post-Training](https://mlsanity.com/paper/2607.02840/) (2026)
- [CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning](https://mlsanity.com/paper/2607.29172/) (2026)
- [HumanTracker: Towards Comprehensive and Human-Aligned Motion Tracking Benchmark](https://mlsanity.com/paper/2608.13555/) (2026)

## Abstract (arXiv)

The primary obstacle for applying reinforcement learning (RL) to real-world robotics is the design of effective reward functions. While recently learning-based Process Reward Models (PRMs) are a promising direction, they are often hindered by two fundamental limitations: their reward models lack step-aware understanding and rely on single-view perception, leading to unreliable assessments of fine-grained manipulation progress; and their reward shaping procedures are theoretically unsound, often inducing a semantic trap that misguides policy optimization. To address these, we introduce Dopamine-Reward, a novel reward modeling method for learning a general-purpose, step-aware process reward model from multi-view inputs. At its core is our General Reward Model (GRM), trained on a vast 3,400+ hour dataset, which leverages Step-wise Reward Discretization for structural understanding and Multi-Perspective Reward Fusion to overcome perceptual limitations. Building upon Dopamine-Reward, we propose Dopamine-RL, a robust policy learning framework that employs a theoretically-sound Policy-Invariant Reward Shaping method, which enables the agent to leverage dense rewards for efficient self-improvement without altering the optimal policy, thereby fundamentally avoiding the semantic trap. Extensive experiments across diverse simulated and real-world tasks validate our approach. GRM achieves state-of-the-art accuracy in reward assessment, and Dopamine-RL built on GRM significantly improves policy learning efficiency. For instance, after GRM is adapted to a new task in a one-shot manner from a single expert trajectory, the resulting reward model enables Dopamine-RL to improve the policy from near-zero to 95% success with only 150 online rollouts (approximately 1 hour of real robot interaction), while retaining strong generalization across tasks. Project website: https://robo-dopamine.github.io