# Repro - Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks

## Pages

| Page |
| --- |
| [Paper version and claim map](#/paper-version-and-claim-map) |
| [Claim 1 - Closed-form optimal control](#/claim-1-closed-form-optimal-control) |
| [Claim 2 - Analytic and neural returns](#/claim-2-analytic-and-neural-returns) |
| [Claim 3 - CH-3-ARS](#/claim-3-ch-3-ars) |
| [Claim 4 - CH-3-PPO and CH-3-REINFORCE](#/claim-4-ch-3-ppo-and-ch-3-reinforce) |
| [Claim 5 - Pendulum and Aero 2](#/claim-5-pendulum-and-aero-2) |
| [Conclusion](#/conclusion) |