# Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning

arXiv: https://arxiv.org/abs/2111.03189 · HTML: https://mlsanity.com/paper/2111.03189/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 60 of its 100 references that are in the map.
- First posted on arXiv 4 Nov 2021.

## Builds on (most cited first, 30 of 60)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Rainbow: Combining Improvements in Deep Reinforcement Learning](https://mlsanity.com/paper/1710.02298/) (2017)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [A Distributional Perspective on Reinforcement Learning](https://mlsanity.com/paper/1707.06887/) (2017)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [The Option-Critic Architecture](https://mlsanity.com/paper/1609.05140/) (2016)
- [Learning Invariant Representations for Reinforcement Learning without Reconstruction](https://mlsanity.com/paper/2006.10742/) (2020)
- [Reinforcement Learning with Unsupervised Auxiliary Tasks](https://mlsanity.com/paper/1611.05397/) (2016)
- [Dynamics-Aware Unsupervised Discovery of Skills](https://mlsanity.com/paper/1907.01657/) (2019)
- [Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation](https://mlsanity.com/paper/1604.06057/) (2016)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://mlsanity.com/paper/1506.07365/) (2015)
- [Improving Sample Efficiency in Model-Free Reinforcement Learning from Images](https://mlsanity.com/paper/1910.01741/) (2019)
- [Visual Reinforcement Learning with Imagined Goals](https://mlsanity.com/paper/1807.04742/) (2018)
- [Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model](https://mlsanity.com/paper/1907.00953/) (2019)
- [MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale](https://mlsanity.com/paper/2104.08212/) (2021)
- [Semi-parametric Topological Memory for Navigation](https://mlsanity.com/paper/1803.00653/) (2018)
- [Search on the Replay Buffer: Bridging Planning and Reinforcement Learning](https://mlsanity.com/paper/1906.05253/) (2019)
- [Soft Actor-Critic for Discrete Action Settings](https://mlsanity.com/paper/1910.07207/) (2019)
- [DARLA: Improving Zero-Shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/1707.08475/) (2017)

## Built on by (most cited first, 26 of 26)

- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [Policy Expansion for Bridging Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2302.00935/) (2023)
- [Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models](https://mlsanity.com/paper/2401.03360/) (2023)
- [Latent Plans for Task-Agnostic Offline Reinforcement Learning](https://mlsanity.com/paper/2209.08959/) (2022)
- [Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents](https://mlsanity.com/paper/2303.00855/) (2023)
- [LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents](https://mlsanity.com/paper/2402.08178/) (2024)
- [Skill-based Model-based Reinforcement Learning](https://mlsanity.com/paper/2207.07560/) (2022)
- [LangNav: Language as a Perceptual Representation for Navigation](https://mlsanity.com/paper/2310.07889/) (2023)
- [CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models](https://mlsanity.com/paper/2409.18382/) (2024)
- [RoboMatrix: A Skill-centric Hierarchical Framework for Scalable Robot Task Planning and Execution in Open-World](https://mlsanity.com/paper/2412.00171/) (2024)
- [Generating Executable Action Plans with Environmentally-Aware Language Models](https://mlsanity.com/paper/2210.04964/) (2022)
- [Stitching Sub-Trajectories with Conditional Diffusion Model for Goal-Conditioned Offline RL](https://mlsanity.com/paper/2402.07226/) (2024)
- [STAP: Sequencing Task-Agnostic Policies](https://mlsanity.com/paper/2210.12250/) (2022)
- [GALOIS: Boosting Deep Reinforcement Learning via Generalizable Logic Synthesis](https://mlsanity.com/paper/2205.13728/) (2022)
- [Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning](https://mlsanity.com/paper/2310.00229/) (2023)
- [Compose by Focus: Scene Graph-based Atomic Skills](https://mlsanity.com/paper/2509.16053/) (2025)
- [RoboMP2: A Robotic Multimodal Perception-Planning Framework with Multimodal Large Language Models](https://mlsanity.com/paper/2404.04929/) (2024)
- [Learning Planning Abstractions from Language](https://mlsanity.com/paper/2405.03864/) (2024)
- [Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation](https://mlsanity.com/paper/2412.20338/) (2024)
- [Hierarchical Reinforcement Learning in Complex 3D Environments](https://mlsanity.com/paper/2302.14451/) (2023)
- [Future Predictive Success-or-Failure Classification for Long-Horizon Robotic Tasks](https://mlsanity.com/paper/2404.03415/) (2024)
- [Goal Exploration via Adaptive Skill Distribution for Goal-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2404.12999/) (2024)
- [Learning telic-controllable state representations](https://mlsanity.com/paper/2406.14476/) (2024)
- [Training Generalist Navigation Policies via Action Self-Distillation](https://mlsanity.com/paper/2610.17593/) (2026)

## Abstract (arXiv)

Reinforcement learning can train policies that effectively perform complex tasks. However for long-horizon tasks, the performance of these methods degrades with horizon, often necessitating reasoning over and chaining lower-level skills. Hierarchical reinforcement learning aims to enable this by providing a bank of low-level skills as action abstractions. Hierarchies can further improve on this by abstracting the space states as well. We posit that a suitable state abstraction should depend on the capabilities of the available lower-level policies. We propose Value Function Spaces: a simple approach that produces such a representation by using the value functions corresponding to each lower-level skill. These value functions capture the affordances of the scene, thus forming a representation that compactly abstracts task relevant information and robustly ignores distractors. Empirical evaluations for maze-solving and robotic manipulation tasks demonstrate that our approach improves long-horizon performance and enables better zero-shot generalization than alternative model-free and model-based methods.