HomeSort by relevance Sort by last modified time
    Searched refs:reward (Results 1 - 2 of 2) sorted by null

  /external/tensorflow/tensorflow/contrib/autograph/examples/benchmarks/
cartpole_benchmark.py 19 by the episode's cumulative discounted reward and averages these gradients over
147 obs, reward, done = cart_pole_env.step(actions)
152 game_rewards.append(reward)
153 if reward < 0.1 or done:
224 obs, reward, done, _ = self.env.step(actions)
226 reward = np.float32(reward)
227 return obs, reward, done
336 obs, reward, done = cart_pole_env.step(actions)
338 game_rewards.append(reward)
    [all...]
  /external/tensorflow/tensorflow/python/grappler/
hierarchical_controller.py 270 reward = run_time
272 reward = math.sqrt(run_time)
274 reward = math.log1p(run_time)
277 "Unrecognized reward function '%s', consider your "
279 return reward
298 ctr["reward"] = {"value": [], "ph": [], "update": []}
311 ctr["reward"]["value"].append(reward_value)
312 ctr["reward"]["ph"].append(reward_ph)
313 ctr["reward"]["update"].append(reward_update)
353 ctr["reward"]["value"]
    [all...]

Completed in 2975 milliseconds