Skip to content

Instantly share code, notes, and snippets.

@ravishchawla

ravishchawla/rl_hyperparams.csv

Last active December 6, 2019 18:00
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save ravishchawla/040a5ea0cfe08a8797bbfd4c11cc65e4 to your computer and use it in GitHub Desktop.
Save ravishchawla/040a5ea0cfe08a8797bbfd4c11cc65e4 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
rl_hyperparams.csv
Agent Hyperparameters
Replay Buffer Size 1e5
Minibatch Size 128
Discount Rate 0.99
TAU 1e-3
Actor Learning Rate 1e-4
Critic Learning Rate 1e-4
L2 Weight Decay 1e-6
Actor Model Hyperparameters
Input Layer 24x128
BatchNorm Layer 128
Dense Hidden Layer 128x64
Output Layer 64x2
Critic Model Hyperparameters
Input Layer 24x128
BatchNorm Layer 128
Dense Hidden Layer 130x64
Dropout Layer 0.2
Output Layer 64x2
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment