Commit 07ac8209 authored by Benjamin Beyret's avatar Benjamin Beyret
Browse files

clean PPO cofiguration file

parent 8e2c397a
default:
Learner:
trainer: ppo
batch_size: 1024
beta: 5.0e-3
buffer_size: 10240
epsilon: 0.2
gamma: 0.99
hidden_units: 128
lambd: 0.95
learning_rate: 3.0e-4
max_steps: 5.0e4
memory_size: 256
normalize: false
num_epoch: 3
num_layers: 2
time_horizon: 64
sequence_length: 64
summary_freq: 1000
use_recurrent: false
use_curiosity: false
curiosity_strength: 0.01
curiosity_enc_size: 128
Learner:
use_curiosity: true
curiosity_strength: 0.01
curiosity_enc_size: 256
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment