wassname/DeepRL
1
0
Fork 0
mirror of https://github.com/wassname/DeepRL.git synced 2026-09-09 11:13:47 +08:00
Code Issues Packages Projects Releases Wiki Activity

Tune parameters

Browse Source
This commit is contained in:
Shangtong Zhang
2017-06-05 15:23:41 -06:00
parent a9d4a0fa72
commit af17bbbf94
1 changed files with 4 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
main.py
+4 -5
View File
@@ -89,24 +89,23 @@ def dqn_pixel_atari(name):
def async_pixel_atari(name): def async_pixel_atari(name):
config = dict() config = dict()
history_length = 1 history_length = 4
n_actions = 6 n_actions = 6
config['task_fn'] = lambda: PixelAtari(name, no_op=30, frame_skip=4) config['task_fn'] = lambda: PixelAtari(name, no_op=30, frame_skip=4)
config['optimizer_fn'] = lambda params: torch.optim.Adam(params, lr=0.0001) config['optimizer_fn'] = lambda params: torch.optim.Adam(params, lr=0.0001)
# config['optimizer_fn'] = lambda params: torch.optim.RMSprop(params, lr=0.0001)
config['network_fn'] = lambda: NipsConvNet(history_length, n_actions, gpu=False) config['network_fn'] = lambda: NipsConvNet(history_length, n_actions, gpu=False)
config['policy_fn'] = lambda: StochasticGreedyPolicy(epsilons=[1.0, 1.0, 1.0], config['policy_fn'] = lambda: StochasticGreedyPolicy(epsilons=[1.0, 1.0, 1.0],
final_step=int(4000000/16), final_step=1000000,
min_epsilons=[0.1, 0.01, 0.5], min_epsilons=[0.1, 0.01, 0.5],
probs=[0.4, 0.3, 0.3]) probs=[0.4, 0.3, 0.3])
# config['bootstrap_fn'] = OneStepQLearning # config['bootstrap_fn'] = OneStepQLearning
# config['bootstrap_fn'] = NStepQLearning # config['bootstrap_fn'] = NStepQLearning
config['bootstrap_fn'] = OneStepSarsa config['bootstrap_fn'] = OneStepSarsa
config['discount'] = 0.99 config['discount'] = 0.99
config['target_network_update_freq'] = 40000 config['target_network_update_freq'] = 10000
config['step_limit'] = 10000 config['step_limit'] = 10000
config['n_workers'] = 16 config['n_workers'] = 16
config['batch_size'] = 20 config['batch_size'] = 32
config['test_interval'] = 50000 config['test_interval'] = 50000
config['test_repetitions'] = 1 config['test_repetitions'] = 1
config['history_length'] = history_length config['history_length'] = history_length