mlsanityData to 7 Oct 2026

Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning

arXiv 2503.05042 ↗First posted 6 Mar 2025cs.LG cs.AI cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Automata-conditioned reinforcement learning (RL) has given promising results for learning multi-task policies capable of performing temporally extended objectives given at runtime, done by pretraining and freezing automata embeddings prior to training the downstream policy. However, no theoretical guarantees were given. This work provides a theoretical framework for the automata-conditioned RL problem and shows that it is probably approximately correct learnable. We then present a technique for learning provably correct automata embeddings, guaranteeing optimal multi-task policy learning. Our experimental evaluation confirms these theoretical results.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 15 of its 22 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

15 of 22 references.

References · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  3. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  4. 2021How Attentive are Graph Attention Networks?cited by 818
  5. 2020Learning Invariant Representations for Reinforcement Learning without Reconstructioncited by 424
  6. 2023Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learningcited by 155
  7. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 145
  8. 2019Scalable methods for computing state similarity in deterministic Markov Decision Processescited by 133
  9. 2023RoboCLIP: One Demonstration is Enough to Learn Robot Policiescited by 128
  10. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 72
  11. 2021Compositional Reinforcement Learning from Logical Specificationscited by 65
  12. 2025Motion Tracks: A Unified Representation for Human-Robot Transfer in Few-Shot Imitation Learningcited by 57
3 more
  1. 2021On the (In)Tractability of Reinforcement Learning for LTL Objectivescited by 18
  2. 2024Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learningcited by 18
  3. 2023Policy Synthesis and Reinforcement Learning for Discounted LTLcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learningcited by 8
  2. 2026Event-B Agent: Towards LLM Agent for Formal Model Synthesis and Repaircited by 3
  3. 2025Automata-Conditioned Cooperative Multi-Agent Reinforcement Learningcited by 1
  4. 2026Controllability in preference-conditioned multi-objective reinforcement learningcited by 1