search

MSRDL / baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
MIT License
0 stars 0 forks source link

Add NAF #1

Closed zer0n closed 6 years ago

zer0n commented 6 years ago

Full name: Continuous Deep Q-Learning with model-based acceleration

This paper is [9] in the DeepPILCO paper.

Both this and DeepPILCO will serve as baselines for our work.

zer0n commented 6 years ago

Existing implementations: 1, 2, ...

There are many existing implementations on GitHub --> pick the one that mirrors the paper and is cleanest.