MCPcopy
hub / github.com/tensorlayer/TensorLayer / tutorial_TD3.py

File tutorial_TD3.py

examples/reinforcement_learning/tutorial_TD3.py:None–None  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1"""
2Twin Delayed DDPG (TD3)
3------------------------
4DDPG suffers from problems like overestimate of Q-values and sensitivity to hyper-parameters.

Callers

nothing calls this directly

Calls 10

TD3Class · 0.85
ReplayBufferClass · 0.70
resetMethod · 0.45
get_actionMethod · 0.45
sample_actionMethod · 0.45
stepMethod · 0.45
pushMethod · 0.45
updateMethod · 0.45
saveMethod · 0.45
loadMethod · 0.45

Tested by

no test coverage detected