mlsanityData to 7 Oct 2026

What can I do here? A Theory of Affordances in Reinforcement Learning

arXiv 2006.15085 ↗First posted 26 Jun 2020cs.LG cs.AI stat.MLcited by 33

Not on the map. Why?

Abstract (arXiv)

Reinforcement learning algorithms usually assume that all actions are always available to an agent. However, both people and animals understand the general link between the features of their environment and the actions that are feasible. Gibson (1977) coined the term "affordances" to describe the fact that certain states enable an agent to do certain actions, in the context of embodied agents. In this paper, we develop a theory of affordances for agents who learn and plan in Markov Decision Processes. Affordances play a dual role in this case. On one hand, they allow faster planning, by reducing the number of actions available in any given situation. On the other hand, they facilitate more efficient and precise learning of transition models from data, especially when such models require function approximation. We establish these properties through theoretical results as well as illustrative examples. We also propose an approach to learn affordances and use it to estimate transition models that are simpler and generalize better.

Key facts. Cited by 33 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 10; 2023: 6; 2024: 3; 2025: 2; 2026: 4.

33 papers.

Sort:

By area:

  1. 2024Code as Reward: Empowering Reinforcement Learning with VLMscited by 38
  2. 2021Iterative Bounding MDPs: Learning Interpretable Policies via Non-Interpretable Methodscited by 31
  3. 2023CCIL: Continuity-based Data Augmentation for Corrective Imitation Learningcited by 26
  4. 2021What Can I Do Here? Learning New Skills by Imagining Visual Affordancescited by 22
  5. 2021HALMA: Humanlike Abstraction Learning Meets Affordance in Rapid Problem Solvingcited by 15
  6. 2022Goal-Space Planning with Subgoal Modelscited by 12
  7. 2021Temporally Abstract Partial Modelscited by 11
  8. 2021Adjacency constraint for efficient hierarchical reinforcement learningcited by 10
  9. 2022Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learningcited by 10
  10. 2023Recent Advances of Deep Robotic Affordance Learning: A Reinforcement Learning Perspectivecited by 10
  11. 2022A Rubric for Human-like Agents and NeuroAIcited by 8
  12. 2022Complex behavior from intrinsic motivation to occupy action-state path spacecited by 7
21 more
  1. 2024Learning Action-based Representations Using Invariancecited by 5
  2. 2021Rediscovering Affordance: A Reinforcement Learning Perspectivecited by 4
  3. 2022Possibility Before Utility: Learning And Using Hierarchical Affordancescited by 4
  4. 2022Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RLcited by 4
  5. 2023Knowledge-Guided Short-Context Action Anticipation in Human-Centric Videoscited by 4
  6. 2022The Paradox of Choice: Using Attention in Hierarchical Reinforcement Learningcited by 2
  7. 2022GrASP: Gradient-Based Affordance Selection for Planningcited by 2
  8. 2023Minimal Value-Equivalent Partial Models for Scalable and Robust Planning in Lifelong Reinforcement Learningcited by 2
  9. 2023Efficient Learning of High Level Plans from Playcited by 2
  10. 2023Self-Supervised Learning of Action Affordances as Interaction Modescited by 2
  11. 2022Affordance Extraction with an External Knowledge Database for Text-Based Simulated Environmentscited by 1
  12. 2025Cracking the Code of Action: a Generative Approach to Affordances for Reinforcement Learningcited by 1
  13. 2026Joint Learning of Hierarchical Neural Options and Abstract World Modelcited by 1
  14. 2026Toward Enactive Artificial Intelligencecited by 1
  15. 2021Individual and Collective Autonomous Developmentcited by 0
  16. 2021Bayesian deep learning of affordances from RGB imagescited by 0
  17. 2022Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learningcited by 0
  18. 2024Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learningcited by 0
  19. 2025A Unified Theory of Compositionality, Modularity, and Interpretability in Markov Decision Processescited by 0
  20. 2026Overcoming Valid Action Suppression in Unmasked Policy Gradient Algorithmscited by 0
  21. 2026Synthetic Linguistic Agency: How an Embodied Mortal Agent Learns Linguistic Affordances through Consequential Social Experiencecited by 0