A reinforcement learning system that trains a PPO agent to dynamically price products in a simulated competitive retail market, calibrated on real retail transactions, tested across 5 shock scenarios and 5 competitor archetypes.
Train a reinforcement learning agent using PPO to balance a pole on a cart in the CartPole-v0 environment using Gymnasium and Stable-Baselines3. Includes model training, evaluation, and rendering using Python and Jupyter Notebook.
Q-Learning, SARSA, and DQN implemented from scratch and benchmarked across 4 OpenAI Gymnasium environments — tabular vs. neural network approximation, with hyperparameter tuning and reward shaping.
Benchmarking DQN, Double-DQN, and PPO on OpenAI Gymnasium's CarRacing-v3 using PyTorch. Includes a one-click Google Colab notebook and a unified benchmark framework with reward curves, leaderboards, and reproducibility configs.
Add a description, image, and links to the openai-gymnasium topic page so that developers can more easily learn about it.
To associate your repository with the openai-gymnasium topic, visit your repo's landing page and select "manage topics."