zoo.examples.ray.rl_pong package

Submodules

zoo.examples.ray.rl_pong.rl_pong module

zoo.examples.ray.rl_pong.rl_pong.discount_rewards(r)[source]

take 1D float array of rewards and compute discounted reward

zoo.examples.ray.rl_pong.rl_pong.policy_backward(eph, epx, epdlogp, model)[source]

backward pass. (eph is array of intermediate hidden states)

zoo.examples.ray.rl_pong.rl_pong.policy_forward(x, model)[source]
zoo.examples.ray.rl_pong.rl_pong.preprocess(img)[source]

Preprocess 210x160x3 uint8 frame into 6400 (80x80) 1D float vector.

zoo.examples.ray.rl_pong.rl_pong.sigmoid(x)[source]

Module contents