hub / github.com/Yonv1943/Python / run__tutorial_discrete_action

Function run__tutorial_discrete_action

Demo_deep_learning/Tutorial.py:179–324 · view source on GitHub ↗

It is a DQN tutorial, we need 1min for training. This simplify DQN can't work well on harder task. Other RL algorithms can work well on harder task but complicated. You can change this code and make the training finish in (10 sec, 10k step) as an execrise.

()

Source from the content-addressed store, hash-verified

source not stored for this graph (policy: none)

Callers 1

Tutorial.pyFile · 0.85

Calls 10

get_eva_reward__svMethod · 0.95

add_memoMethod · 0.95

init_before_sampleMethod · 0.95

random_sampleMethod · 0.95

EvaluateRewardSVClass · 0.85

QNetClass · 0.70

BufferArrayClass · 0.70

soft_target_updateFunction · 0.70

resetMethod · 0.45

stepMethod · 0.45

Tested by

no test coverage detected