mlsanityData to 7 Oct 2026

Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents

arXiv 2202.05129 ↗First posted 10 Feb 2022cs.AI cs.HCcited by 3

Not on the map. Why?

Abstract (arXiv)

In the quest for autonomous agents learning open-ended repertoires of skills, most works take a Piagetian perspective: learning trajectories are the results of interactions between developmental agents and their physical environment. The Vygotskian perspective, on the other hand, emphasizes the centrality of the socio-cultural environment: higher cognitive functions emerge from transmissions of socio-cultural processes internalized by the agent. This paper argues that both perspectives could be coupled within the learning of autotelic agents to foster their skill acquisition. To this end, we make two contributions: 1) a novel social interaction protocol called Help Me Explore (HME), where autotelic agents can benefit from both individual and socially guided exploration. In social episodes, a social partner suggests goals at the frontier of the learning agent knowledge. In autotelic episodes, agents can either learn to master their own discovered goals or autonomously rehearse failed social goals; 2) GANGSTR, a graph-based autotelic agent for manipulation domains capable of decomposing goals into sequences of intermediate sub-goals. We show that when learning within HME, GANGSTR overcomes its individual learning limits by mastering the most complex configurations (e.g. stacks of 5 blocks) with only few social interventions.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 30 of its 71 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

30 of 71 references.

References · 30

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  3. 2017Deep reinforcement learning from human preferencescited by 3,846
  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. 2018Diversity is All You Need: Learning Skills without a Reward Functioncited by 734
  9. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 632
  10. 2018Large-Scale Study of Curiosity-Driven Learningcited by 277
  11. 2019Self-Supervised Exploration via Disagreementcited by 263
  12. 2018Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Researchcited by 256
18 more
  1. 2020First return, then explorecited by 256
  2. 2018Visual Reinforcement Learning with Imagined Goalscited by 248
  3. 2019Go-Explore: a New Approach for Hard-Exploration Problemscited by 207
  4. 2019Skew-Fit: State-Covering Self-Supervised Reinforcement Learningcited by 171
  5. 2020Automatic Curriculum Learning For Deep RL: A Short Surveycited by 141
  6. 2018Unsupervised Control Through Non-Parametric Discriminative Rewardscited by 102
  7. 2017Surprise-Based Intrinsic Motivation for Deep Reinforcement Learningcited by 83
  8. 2020Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Surveycited by 83
  9. 2017Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learningcited by 79
  10. 2018CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learningcited by 78
  11. 2020Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Explorationcited by 68
  12. 2013Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robotscited by 56
  13. 2019Contextual Imagined Goals for Self-Supervised Robotic Learningcited by 40
  14. 2019Unsupervised Grounding of Plannable First-Order Logic Representation from Imagescited by 24
  15. 2019CLIC: Curriculum Learning and Imitation for object Control in non-rewarding environmentscited by 10
  16. 2018Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learnercited by 5
  17. 2018Socially Guided Intrinsic Motivation for Robot Learning of Motor Skillscited by 5
  18. 2020Deep Sets for Generalization in RLcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 3.

3 papers.

  1. 2022Pragmatically Learning from Pedagogical Demonstrations in Multi-Goal Environmentscited by 2
  2. 2022Pedagogical Demonstrations and Pragmatic Learning in Artificial Tutor-Learner Interactionscited by 1
  3. 2022Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learningcited by 1