mirror of
https://github.com/vale981/ray
synced 2025-03-08 19:41:38 -05:00
25 lines
641 B
YAML
25 lines
641 B
YAML
|
cartpole-r2d2:
|
||
|
|
env: CartPole-v0
|
||
|
|
run: R2D2
|
||
|
|
stop:
|
||
|
|
episode_reward_mean: 150
|
||
|
|
timesteps_total: 1000000
|
||
|
|
config:
|
||
|
|
# Works for both torch and tf.
|
||
|
|
framework: tf
|
||
|
|
num_workers: 0
|
||
|
|
# R2D2 settings.
|
||
|
|
burn_in: 20
|
||
|
|
zero_init_states: true
|
||
|
|
dueling: false
|
||
|
|
lr: 0.0005
|
||
|
|
# Give some more time to explore.
|
||
|
|
exploration_config:
|
||
|
|
epsilon_timesteps: 100000
|
||
|
|
# Wrap with an LSTM and use a very simple base-model.
|
||
|
|
model:
|
||
|
|
fcnet_hiddens: [32]
|
||
|
|
use_lstm: true
|
||
|
|
lstm_cell_size: 64
|
||
|
|
max_seq_len: 20
|