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

arXiv:2609.38065 · cs.LG, cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/mathiasj33/jaxolotl

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes

Sources

• PlatoLTL: Scaling LTL-Guided Multi-Task RL
• How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments
• JaxUED: A simple and useable UED library in Jax
• Logically-Constrained Reinforcement Learning
• Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text
• Systematic Generalisation through Task Temporal Logic and Deep Reinforcement Learning
• Grounding LTL Tasks in Sub-Symbolic RL Environments for Zero-Shot Generalization
• Proximal Policy Optimization Algorithms
• MuJoCo Playground
• Composing Learned Robot Behaviors with Temporal Logic at Runtime

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks