Skip to content

Latest commit

 

History

History
43 lines (34 loc) · 892 Bytes

README.md

File metadata and controls

43 lines (34 loc) · 892 Bytes

DQN in R

Simple DQN implementation in R
Original Paper: Playing Atari with Deep Reinforcement Learning

Pseudocode

UML

Gym stat

Link: https://gym.openai.com/evaluations/eval_iEDX4AWFRmu8gqoIkmlXA

Dependencies

  • tensorflow
  • reticulate

Files

.
├── Agent.R # Agent class is defined here
├── assets 
├── DQN-in-R.Rproj
├── main.R # the main file to run
├── Memory.R # Memory class is defined here (aka Experience Replay Memory)
├── README.md
└── train.R # training helper function