def wang2015_eval(game_name, act, stochastic):
print("==================== wang2015 evaluation ====================")
episode_rewards = []
for num_noops in range(1, 31):
env_monitored, eval_env = make_env(game_name)
eval_env.unwrapped.seed(1)
get_wrapper_by_name(eval_env, "NoopResetEnv").override_num_noops = num_noops
eval_episode_steps = 0
done = True
while True:
if done:
obs = eval_env.reset()
eval_episode_steps += 1
action = act(np.array(obs)[None], stochastic=stochastic)[0]
obs, reward, done, info = eval_env.step(action)
if done:
obs = eval_env.reset()
if len(info["rewards"]) > 0:
episode_rewards.append(info["rewards"][0])
break
if info["steps"] > 108000: # 5 minutes of gameplay
episode_rewards.append(env_monitored._current_reward)
break
print("Num steps in episode {} was {} yielding {} reward".format(
num_noops, eval_episode_steps, episode_rewards[-1]), flush=True)
print("Evaluation results: " + str(np.mean(episode_rewards)))
print("=============================================================")
return np.mean(episode_rewards)
def wang2015_eval(game_name, act, stochastic):
print("==================== wang2015 evaluation ====================")
episode_rewards = []
for num_noops in range(1, 31):
env_monitored, eval_env = make_env(game_name)
eval_env.unwrapped.seed(1)
get_wrapper_by_name(eval_env,
"NoopResetEnv").override_num_noops = num_noops
eval_episode_steps = 0
done = True
while True:
if done:
obs = eval_env.reset()
eval_episode_steps += 1
action = act(np.array(obs)[None], stochastic=stochastic)[0]
obs, _reward, done, info = eval_env.step(action)
if done:
obs = eval_env.reset()
if len(info["rewards"]) > 0:
episode_rewards.append(info["rewards"][0])
break
if info["steps"] > 108000: # 5 minutes of gameplay
episode_rewards.append(sum(env_monitored.rewards))
break
print("Num steps in episode {} was {} yielding {} reward".format(
num_noops, eval_episode_steps, episode_rewards[-1]),
flush=True)
print("Evaluation results: " + str(np.mean(episode_rewards)))
print("=============================================================")
return np.mean(episode_rewards)