Code
Hub
Workspaces
Connect
Indexed graphs
Engine
MCP
copy
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
3
Mnih et al., 2015: "Human-level control through deep reinforcement
4
learning" (Nature). Same algorithm
as
the cartpole DQN but
with
the
Callers
nothing calls this directly
Calls
15
parse_args
Function · 0.90
pick_device
Function · 0.90
make_env
Function · 0.90
run_test_loop
Function · 0.90
quit_if_window_closed
Function · 0.90
ReplayBuffer
Class · 0.85
epsilon
Function · 0.85
greedy_action
Function · 0.85
push
Method · 0.80
append
Method · 0.80
QNetwork
Class · 0.70
reset
Method · 0.45
Tested by
no test coverage detected