AWS DeepRacer Fun

Reward Function

• Framework: Tensorflow
• Reinforcement learning algorithm: Proximal Policy Optimization (PPO)
• Reward function execution environment: python3.5

Running Locally

$ pip3.5 install -r requirements.txt
$ python3.5 -m pytest -s

Good Reading

DeepRacer

• AWS Workshop README
• BeGreat Medium Post
• Reward Function Input Parameters
• Sharing my Reward Functions so far...
• AWS DeepRacer— Everything that you need to know regarding training

Reinforcement Learning

• Youtube: Writing Great Reward Functions

PPO Algorithm

• OpenAI Introducing PPO to the World
• RL — Proximal Policy Optimization (PPO) Explained
• Introduction to Various Reinforcement Learning Algorithms. Part II (TRPO, PPO)
• Proximal Policy Optimization (PPO) with Sonic the Hedgehog 2 and 3