mlsanityData to 14 Oct 2026

Jaxolotl: A Unified High-Performance Benchmark Suite for LTL-Based Multi-Task RL

arXiv 2609.38065 ↗First posted 29 Sep 2026cs.LG cs.AIcited by 0

On the map: Deep reinforcement learning methods → Interpretable and logic-guided RL

Abstract (arXiv)

Training agents to follow arbitrary instructions is an important goal of multi-task reinforcement learning (RL). Linear temporal logic (LTL) provides a precise and structured formalism for specifying instructions to agents, and has been successfully adopted for training generalist multi-task policies. However, differences in implementations, task distributions, and evaluation protocols make existing methods difficult to compare, while high computational costs limit the scale and statistical reliability of experiments. We introduce Jaxolotl, a unified high-performance benchmark suite for multi-task LTL-RL to address these concerns. Jaxolotl provides a modular, end-to-end JAX implementation of six representative algorithms and four environments, together with newly curated task suites and a standardised, statistically robust evaluation protocol. By precompiling symbolic task representations into static arrays, Jaxolotl enables fully JIT-compiled training and evaluation, achieving end-to-end speedups of up to 220× and supporting controlled comparisons at substantially greater experimental scale. We use this framework to systematically evaluate existing approaches, revealing complementary strengths and limitations: general methods capable of non-myopic reasoning struggle as the number of propositions grows, while methods with stronger scaling rely on environment-specific assumptions and suffer from myopia.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods. Builds on 73 of its 93 references that are in the map. First posted on arXiv 29 Sep 2026.

Builds on

73 of 93 references.

Closest ancestors · 12

Same direction, newest first

  1. 2026SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning27 Apr
  2. 2026Zero-Shot Instruction Following in RL via Structured LTL Representations15 Feb
  3. 2026Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization10 Feb
  4. 2026Semantically Labelled Automata for Multi-Task Reinforcement Learning with LTL Instructions6 Feb
  5. 2026PlatoLTL: Scaling LTL-Guided Multi-Task RL30 Jan
  6. 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learning3 Aug
  7. 2024Exploiting Hybrid Policy in Reinforcement Learning for Interpretable Temporal Logic Manipulation29 Dec
  8. 2024Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning31 Oct
  9. 2024DeepLTL: Learning to Efficiently Satisfy Complex LTL Specifications for Multi-Task RL6 Oct
  10. 2024Directed Exploration in Reinforcement Learning from Linear Temporal Logic18 Aug
  11. 2024Neural Reward Machines16 Aug
  12. 2024Inductive Generalization in Reinforcement Learning from Specifications5 Jun

Other references · 61

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  4. 2017Deep Setscited by 1,421
  5. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  6. 2021Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolationcited by 1,103
  7. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  8. 2017Deep Reinforcement Learning that Matterscited by 754
  9. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 407
  10. 2018BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learningcited by 244
  11. 2016Modular Multitask Reinforcement Learning with Policy Sketchescited by 203
  12. 2023Grounding Large Language Models in Interactive Environments with Online Reinforcement Learningcited by 195
38 more
  1. 2020Reward Machines: Exploiting Reward Function Structure in Reinforcement Learningcited by 191
  2. 2022Goal-Conditioned Reinforcement Learning: Problems and Solutionscited by 158
  3. 2019A Survey of Reinforcement Learning Informed by Natural Languagecited by 154
  4. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  5. 2016Reinforcement Learning With Temporal Logic Rewardscited by 117
  6. 2022Discovered Policy Optimisationcited by 104
  7. 2017Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learningcited by 98
  8. 2024Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learningcited by 88
  9. 2023OmniSafe: An Infrastructure for Accelerating Safe Reinforcement Learning Researchcited by 80
  10. 2018Omega-Regular Objectives in Model-Free Reinforcement Learningcited by 75
  11. 2019Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learningcited by 75
  12. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 74
  13. 2018Foundations for Restraining Bolts: Reinforcement Learning with LTLf/LDLf restraining specificationscited by 72
  14. 2020A Composable Specification Language for Reinforcement Learning Taskscited by 69
  15. 2016Q-Learning for Robust Satisfaction of Signal Temporal Logic Specificationscited by 67
  16. 2023JaxMARL: Multi-Agent RL Environments and Algorithms in JAXcited by 63
  17. 2018How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experimentscited by 60
  18. 2023nl2spec: Interactively Translating Unstructured Natural Language to Temporal Logics with Large Language Modelscited by 60
  19. 2020Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Textcited by 59
  20. 2023Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAXcited by 58
  21. 2019Joint Inference of Reward Machines and Policies for Reinforcement Learningcited by 56
  22. 2023XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAXcited by 55
  23. 2023Grounding Complex Natural Language Commands for Temporal Tasks in Unseen Environmentscited by 53
  24. 2018Logically-Constrained Reinforcement Learningcited by 51
  25. 2019Measuring the Reliability of Reinforcement Learning Algorithmscited by 51
  26. 2023Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learningcited by 51
  27. 2014A Learning Based Approach to Control Synthesis of Markov Decision Processes for Linear Temporal Logic Specificationscited by 49
  28. 2022skrl: Modular and Flexible Library for Reinforcement Learningcited by 49
  29. 2022Towards a Standardised Performance Evaluation Protocol for Cooperative MARLcited by 49
  30. 2024Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Taskscited by 45
  31. 2018Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependenciescited by 43
  32. 2019Certified Reinforcement Learning with Logic Guidancecited by 36
  33. 2020Evaluating the Performance of Reinforcement Learning Algorithmscited by 36
  34. 2021The Logical Options Frameworkcited by 25
  35. 2020Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learningcited by 21
  36. 2022Policy Optimization with Linear Temporal Logic Constraintscited by 19
  37. 2023Eventual Discounting Temporal Logic Counterfactual Experience Replaycited by 19
  38. 2021On the (In)Tractability of Reinforcement Learning for LTL Objectivescited by 18

50 most cited of 61 All 61 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Temporal Logic Guided Universal Task Representations for Reinforcement Learning
  2. 2025Zero-Shot Instruction Following in RL via Structured LTL Representations
  3. 2026MARLaaS: Multi-Tenant Asynchronous Reinforcement Learning as a Service
  4. 2024Comp-LTL: Temporal Logic Planning via Zero-Shot Policy Composition
  5. 2025Accelerated Learning with Linear Temporal Logic using Differentiable Simulation
  6. 2025AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
  7. 2025Part I: Tricks or Traps? A Deep Dive into RL for LLM Reasoning
  8. 2026Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL