|
|
|
|
|
from easydict import EasyDict |
|
|
|
main_config = dict( |
|
exp_name="hopper_expert_cql_seed0", |
|
env=dict( |
|
env_id='hopper-expert-v0', |
|
collector_env_num=1, |
|
evaluator_env_num=8, |
|
use_act_scale=True, |
|
n_evaluator_episode=8, |
|
stop_value=6000, |
|
), |
|
policy=dict( |
|
cuda=True, |
|
model=dict( |
|
obs_shape=11, |
|
action_shape=3, |
|
), |
|
learn=dict( |
|
data_path=None, |
|
train_epoch=30000, |
|
batch_size=256, |
|
learning_rate_q=3e-4, |
|
learning_rate_policy=1e-4, |
|
learning_rate_alpha=1e-4, |
|
alpha=0.2, |
|
auto_alpha=False, |
|
lagrange_thresh=-1.0, |
|
min_q_weight=5.0, |
|
), |
|
collect=dict(data_type='d4rl', ), |
|
eval=dict(evaluator=dict(eval_freq=500, )), |
|
other=dict(replay_buffer=dict(replay_buffer_size=2000000, ), ), |
|
), |
|
) |
|
|
|
main_config = EasyDict(main_config) |
|
main_config = main_config |
|
|
|
create_config = dict( |
|
env=dict( |
|
type='d4rl', |
|
import_names=['dizoo.d4rl.envs.d4rl_env'], |
|
), |
|
env_manager=dict(type='base'), |
|
policy=dict( |
|
type='cql', |
|
import_names=['ding.policy.cql'], |
|
), |
|
replay_buffer=dict(type='naive', ), |
|
) |
|
create_config = EasyDict(create_config) |
|
create_config = create_config |
|
|
