# Affordance-Guided Reinforcement Learning via Visual Prompting

arXiv: https://arxiv.org/abs/2407.10341 · HTML: https://mlsanity.com/paper/2407.10341/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods.
- Builds on 60 of its 91 references that are in the map.
- First posted on arXiv 14 Jul 2024.

## Placed in

- 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 60)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models](https://mlsanity.com/paper/2307.05973/) (2023)
- [SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities](https://mlsanity.com/paper/2401.12168/) (2024)
- [R3M: A Universal Visual Representation for Robot Manipulation](https://mlsanity.com/paper/2203.12601/) (2022)
- [The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)](https://mlsanity.com/paper/2309.17421/) (2023)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [Learning Robust Rewards with Adversarial Inverse Reinforcement Learning](https://mlsanity.com/paper/1710.11248/) (2017)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [VIMA: General Robot Manipulation with Multimodal Prompts](https://mlsanity.com/paper/2210.03094/) (2022)
- [Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.04803/) (2023)

## Built on by (most cited first, 23 of 23)

- [ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation](https://mlsanity.com/paper/2409.01652/) (2024)
- [LLM Post-Training: A Deep Dive into Reasoning Large Language Models](https://mlsanity.com/paper/2502.21321/) (2025)
- [Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications](https://mlsanity.com/paper/2510.07077/) (2025)
- [Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection](https://mlsanity.com/paper/2412.04455/) (2024)
- [Robotic Visual Instruction](https://mlsanity.com/paper/2505.00693/) (2025)
- [Parallels Between VLA Model Post-Training and Human Motor Learning: Progress, Challenges, and Trends](https://mlsanity.com/paper/2506.20966/) (2025)
- [TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation](https://mlsanity.com/paper/2411.16425/) (2024)
- [Open-World Reinforcement Learning over Long Short-Term Imagination](https://mlsanity.com/paper/2410.03618/) (2024)
- [Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs](https://mlsanity.com/paper/2506.04220/) (2025)
- [The Duality of Generative AI and Reinforcement Learning in Robotics: A Review](https://mlsanity.com/paper/2410.16411/) (2024)
- [VPN: Visual Prompt Navigation](https://mlsanity.com/paper/2508.01766/) (2025)
- [VLA Model Post-Training via Action-Chunked PPO and Self Behavior Cloning](https://mlsanity.com/paper/2509.25718/) (2025)
- [An Anatomy of Vision-Language-Action Models: From Modules to Milestones and Challenges](https://mlsanity.com/paper/2512.11362/) (2025)
- [O3Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation](https://mlsanity.com/paper/2509.06233/) (2025)
- [APEX: Empowering LLMs with Physics-Based Task Planning for Real-time Insight](https://mlsanity.com/paper/2505.13921/) (2025)
- [DORA: Object Affordance-Guided Reinforcement Learning for Dexterous Robotic Manipulation](https://mlsanity.com/paper/2505.14819/) (2025)
- [VLM-TDP: VLM-guided Trajectory-conditioned Diffusion Policy for Robust Long-Horizon Manipulation](https://mlsanity.com/paper/2507.04524/) (2025)
- [Manipulate-to-Navigate: Reinforcement Learning with Visual Affordances and Manipulability Priors](https://mlsanity.com/paper/2508.13151/) (2025)
- [Learning Process Rewards via Success Visitation Matching for Efficient RL](https://mlsanity.com/paper/2606.23640/) (2026)
- [Affordance-Guided Coarse-to-Fine Exploration for Base Placement in Open-Vocabulary Mobile Manipulation](https://mlsanity.com/paper/2511.06240/) (2025)
- [VersualRL: Closed-Loop Verbal Reinforcement Learning with Visual Execution Feedback for Task-Level Robot Planning](https://mlsanity.com/paper/2603.22169/) (2026)
- [AffordMatcher: Affordance Learning in 3D Scenes from Visual Signifiers](https://mlsanity.com/paper/2603.27970/) (2026)
- [GROW2: Grounding Which and Where for Robot Tool Use](https://mlsanity.com/paper/2606.30632/) (2026)

## Abstract (arXiv)

Robots equipped with reinforcement learning (RL) have the potential to learn a wide range of skills solely from a reward signal. However, obtaining a robust and dense reward signal for general manipulation tasks remains a challenge. Existing learning-based approaches require significant data, such as human demonstrations of success and failure, to learn task-specific reward functions. Recently, there is also a growing adoption of large multi-modal foundation models for robotics that can perform visual reasoning in physical contexts and generate coarse robot motions for manipulation tasks. Motivated by this range of capability, in this work, we present Keypoint-based Affordance Guidance for Improvements (KAGI), a method leveraging rewards shaped by vision-language models (VLMs) for autonomous RL. State-of-the-art VLMs have demonstrated impressive zero-shot reasoning about affordances through keypoints, and we use these to define dense rewards that guide autonomous robotic learning. On diverse real-world manipulation tasks specified by natural language descriptions, KAGI improves the sample efficiency of autonomous RL and enables successful task completion in 30K online fine-tuning steps. Additionally, we demonstrate the robustness of KAGI to reductions in the number of in-domain demonstrations used for pre-training, reaching similar performance in 45K online fine-tuning steps. Project website: https://sites.google.com/view/affordance-guided-rl