Solving MountainCar with Intrinsic Curiosity
===
Introduction
---
- [Introduction](/LeXFm3ZWR0eMUm9QEef_MA)
Background
---
- [The MountainCar Environment](/vmuXEJJBQLG4NPuJAvMiMA)
- [Introduction to Q Networks](/ytZnmxRCSdCK2Nc6HvOzjw)
- [Intrinsic Rewards and Curiosity](/Af8sFjoFT3GuzmJo0h8S7A)
Implementation
---
- [Building the Models](/EHmUbglQSU6tz6bwTzfM_w)
- [Collecting Training Data](/7Jg_x1ceTp-Ja9ObrLQhOA)
- [A Single Training Step](/ITMczmZeTXWWNoEWNQ1c1A)
- [The Training Loop](/gJvEgCb9Qwyzf3VCcTjJdg)
- [Learning Rate Decay](/ozXZK5CvQ7WQlILZYHZoIw)
Results
---
- [Results](/VAsST2BPStuw087nsupLQw)
{"metaMigratedAt":"2023-06-16T04:33:32.621Z","metaMigratedFrom":"YAML","title":"Solving MountainCar with Intrinsic Curiosity","breaks":true,"contributors":"[{\"id\":\"d662d8fe-4037-409f-8901-26ee9818bd6f\",\"add\":785,\"del\":135}]"}