mlsanityData to 7 Oct 2026

Learning Object-Centered Autotelic Behaviors with Graph Neural Networks

arXiv 2204.05141 ↗First posted 11 Apr 2022cs.AI cs.LG cs.ROcited by 0

Not on the map. Why?

Abstract (arXiv)

Although humans live in an open-ended world and endlessly face new challenges, they do not have to learn from scratch each time they face the next one. Rather, they have access to a handful of previously learned skills, which they rapidly adapt to new situations. In artificial intelligence, autotelic agents, which are intrinsically motivated to represent and set their own goals, exhibit promising skill adaptation capabilities. However, these capabilities are highly constrained by their policy and goal space representations. In this paper, we propose to investigate the impact of these representations on the learning and transfer capabilities of autotelic agents. We study different implementations of autotelic agents using four types of Graph Neural Networks policy representations and two types of goal spaces, either geometric or predicate-based. By testing agents on unseen goals, we show that combining object-centered architectures that are expressive enough with semantic relational goals helps learning to reach more difficult goals. We also release our graph-based implementations to encourage further research in this direction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 11 Apr 2022.

Builds on

24 of 40 references.

References · 24

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2017Deep Setscited by 1,394
  6. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  7. 2017Hindsight Experience Replaycited by 1,096
  8. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
  9. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  10. 2017A simple neural network module for relational reasoningcited by 345
  11. 2018Large-Scale Study of Curiosity-Driven Learningcited by 277
  12. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 268
12 more
  1. 2019Self-Supervised Exploration via Disagreementcited by 263
  2. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
  3. 2018Visual Reinforcement Learning with Imagined Goalscited by 248
  4. 2019Skew-Fit: State-Covering Self-Supervised Reinforcement Learningcited by 171
  5. 2020Automatic Curriculum Learning For Deep RL: A Short Surveycited by 141
  6. 2017Surprise-Based Intrinsic Motivation for Deep Reinforcement Learningcited by 83
  7. 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 78
  8. 2018Relational Deep Reinforcement Learningcited by 72
  9. 2020Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Explorationcited by 68
  10. 2019Towards Practical Multi-Object Manipulation using Relational Reinforcement Learningcited by 54
  11. 2019Structured agents for physical constructioncited by 50
  12. 2019Curiosity-Driven Multi-Criteria Hindsight Experience Replaycited by 11

Built on by

Not cited yet.