MCPcopy Index your code
hub / github.com/rlcode/reinforcement-learning / 2-ppo.py

File 2-ppo.py

3-atari/2-ppo.py:None–None  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

1"""PPO agent for Atari (Breakout / Pong).
2
3Schulman et al., 2017: "Proximal Policy Optimization Algorithms"
4(arXiv:1707.06347). Same clipped-surrogate + GAE objective as the

Callers

nothing calls this directly

Calls 12

parse_argsFunction · 0.90
pick_deviceFunction · 0.90
make_envFunction · 0.90
run_test_loopFunction · 0.90
make_vec_envFunction · 0.90
appendMethod · 0.80
ActorCriticClass · 0.70
compute_gaeFunction · 0.70
resetMethod · 0.45
sampleMethod · 0.45
stepMethod · 0.45
logMethod · 0.45

Tested by

no test coverage detected