MCPcopy Index your code
hub / github.com/rlcode/reinforcement-learning / 1-dqn.py

File 1-dqn.py

3-atari/1-dqn.py:None–None  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1"""DQN agent for Atari (Breakout / Pong).
2
3Mnih et al., 2015: "Human-level control through deep reinforcement
4learning" (Nature). Same algorithm as the cartpole DQN but with the

Callers

nothing calls this directly

Calls 15

parse_argsFunction · 0.90
pick_deviceFunction · 0.90
make_envFunction · 0.90
run_test_loopFunction · 0.90
quit_if_window_closedFunction · 0.90
ReplayBufferClass · 0.85
epsilonFunction · 0.85
greedy_actionFunction · 0.85
pushMethod · 0.80
appendMethod · 0.80
QNetworkClass · 0.70
resetMethod · 0.45

Tested by

no test coverage detected