mlsanityData to 7 Oct 2026

Learning Embeddings for Sequential Tasks Using Population of Agents

arXiv 2306.03311 ↗First posted 5 Jun 2023cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning. We leverage the idea that two tasks are similar if observing an agent's performance on one task reduces our uncertainty about its performance on the other. This intuition is captured by our information-theoretic criterion which uses a diverse agent population as an approximation for the space of agents to measure similarity between tasks in sequential decision-making settings. In addition to qualitative assessment, we empirically demonstrate the effectiveness of our techniques based on task embeddings by quantitative comparisons against strong baselines on two application scenarios: predicting an agent's performance on a new task by observing its performance on a small quiz of tasks, and selecting tasks with desired characteristics from a given set of options.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 5 Jun 2023.

Builds on

37 of 56 references.

References · 37

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  4. 2016OpenAI Gymcited by 1,684
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  6. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  7. 2019Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variablescited by 372
  8. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 260
  9. 2015Contextual Markov Decision Processescited by 213
  10. 2019Task2Vec: Task Embedding for Meta-Learningcited by 197
  11. 2021Reinforcement Learning with Prototypical Representationscited by 179
  12. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 169
25 more
  1. 2018Meta-Reinforcement Learning of Structured Exploration Strategiescited by 128
  2. 2020Exploring and Predicting Transferability across NLP Taskscited by 126
  3. 2021Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learningcited by 123
  4. 2020STEm-Seg: Spatio-temporal Embeddings for Instance Segmentation in Videoscited by 121
  5. 2020Effective Diversity in Population Based Reinforcement Learningcited by 116
  6. 2019Multimodal Model-Agnostic Meta-Learning via Task-Aware Modulationcited by 103
  7. 2018Leveraging Grammar and Reinforcement Learning for Neural Program Synthesiscited by 83
  8. 2020Self-Paced Deep Reinforcement Learningcited by 49
  9. 2022Bisimulation Makes Analogies in Goal-Conditioned Reinforcement Learningcited by 38
  10. 2022Skill-based Meta-Reinforcement Learningcited by 36
  11. 2019Dynamics-aware Embeddingscited by 34
  12. 2020Towards Effective Context for Meta-Reinforcement Learning: an Approach based on Contrastive Learningcited by 29
  13. 2022Don't Start From Scratch: Leveraging Prior Data to Automate Robotic Reinforcement Learningcited by 28
  14. 2021Self-Paced Context Evaluation for Contextual Reinforcement Learningcited by 25
  15. 2020Domain2Vec: Domain Embedding for Unsupervised Domain Adaptationcited by 24
  16. 2022Wasserstein Task Embedding for Measuring Task Similaritiescited by 24
  17. 2023Proximal Curriculum for Reinforcement Learning Agentscited by 19
  18. 2019Meta Reinforcement Learning with Task Embedding and Shared Policycited by 15
  19. 2021Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learningcited by 15
  20. 2022Multi-Agent Policy Transfer via Task Relationship Modelingcited by 14
  21. 2018Learning to Multitaskcited by 11
  22. 2023Adaptive Scaffolding in Block-Based Programming via Synthesizing New Tasks as Pop Quizzescited by 10
  23. 2021Curriculum Design for Teaching via Demonstrations: Theory and Applicationscited by 9
  24. 2018VPE: Variational Policy Embedding for Transfer Reinforcement Learningcited by 8
  25. 2022Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learningcited by 5

Built on by

Not cited yet.