The purpose of this repository is to provide meaninful baselines for a variety reinforcement learning approaches. The RL approaches are evaluated with an emphasis on the average performance accross multiple agents.
Description: See https://gym.openai.com/envs/CartPole-v1/ for more information. | ||
SGD with feedforward ANN | ||
An inverted pendulum on a cart initially developed by Chuck Anderson ([email protected]). An evaluation episode begins with the pole pointing down, the cart in the center of the track, with both the cart and pole with zero velocity. | ||
SGD with feedforward ANN | Adam with feedforward ANN |