Pendulum

The 'Pendulum' dataset is part of a benchmark used to evaluate reinforcement learning algorithms, specifically in the context of diagnosing non-Markovian observations and their impact on performance metrics.

Papers using Pendulum (3)

Prediction-Based Markov Violation Scores for Detecting Non-Markovian Observations in Reinforcement Learning2026Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM2025Quantifying First-Order Markov Violations in Noisy Reinforcement Learning: A Causal Discovery Approach2025