Jericho

The 'Jericho' dataset is a benchmark used to evaluate the performance of reinforcement learning agents in interactive text-based environments.

Papers using Jericho (4)

PriorZero: Bridging Language Priors and World Models for Decision Making2026Discrete Flow Matching for Offline-to-Online Reinforcement Learning2026Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates2026One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning2025