CartPole

CartPole is a benchmark used in reinforcement learning that involves balancing a pole on a moving cart, evaluating the performance of algorithms in managing this dynamic control task.

Papers using CartPole (21)

Improving the Effectiveness of Potential-Based Reward Shaping in Reinforcement Learning2025 · 2 citesK-score: Kalman Filter As A Principled Alternative To Reward Normalization In Reinforcement Learning2026Residuals-based Offline Reinforcement Learning2026Reinforcement Learning for Control with Probabilistic Stability Guarantee: A Finite-Sample Approach2026Bayesian Conservative Policy Optimization (BCPO): A Novel Uncertainty-Calibrated Offline Reinforcement Learning with Credible Lower Bounds2026Online Adaptive Reinforcement Learning with Echo State Networks for Non-Stationary Dynamics2026A Controlled Study of Double DQN and Dueling DQN Under Cross-Environment Transfer2026Enhanced-FQL($\lambda$), an Efficient and Interpretable RL with novel Fuzzy Eligibility Traces and Segmented Experience Replay2026Learning Without Critics? Revisiting GRPO in Classical Reinforcement Learning Environments2025NFQ2.0: The CartPole Benchmark Revisited2025Heterogeneous Federated Reinforcement Learning Using Wasserstein Barycenters2025SafeRL-Lite: A Lightweight, Explainable, and Constrained Reinforcement Learning Library2025Quantifying First-order Markov Violations In Noisy Reinforcement Learning: A Causal Discovery Approach2025Improving the Data-efficiency of Reinforcement Learning by Warm-starting with LLM2025Bellman operator convergence enhancements in reinforcement learning algorithms2025Using Part-based Representations for Explainable Deep Reinforcement Learning2024 · 2 citesOptimizing Variational Quantum Circuits Using Metaheuristic Strategies in Reinforcement Learning2024Quantifying First-Order Markov Violations in Noisy Reinforcement Learning: A Causal Discovery Approach2025Learning to Control Dynamical Agents via Spiking Neural Networks and Metropolis-Hastings Sampling2025Sampling Complexity of TD and PPO in RKHS2025Diagnosing Non-Markovian Observations in Reinforcement Learning via Prediction-Based Violation Scoring2026