From 7ff1e2f4e4621656f16aee8f523cd9b3e3c88874 Mon Sep 17 00:00:00 2001 From: pranz24 Date: Sun, 7 Apr 2019 23:22:14 +0530 Subject: [PATCH] remove reward list --- main.py | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) diff --git a/main.py b/main.py index e435f82..81ab134 100644 --- a/main.py +++ b/main.py @@ -66,8 +66,6 @@ writer = SummaryWriter(log_dir='runs/{}_SAC_{}_{}_{}'.format(datetime.datetime.n memory = ReplayMemory(args.replay_size) # Training Loop -rewards = [] -test_rewards = [] total_numsteps = 0 updates = 0 @@ -113,8 +111,7 @@ for i_episode in itertools.count(1): break writer.add_scalar('reward/train', episode_reward, i_episode) - rewards.append(episode_reward) - print("Episode: {}, total numsteps: {}, episode steps: {}, reward: {}".format(i_episode, total_numsteps, episode_steps, np.round(rewards[-1],2))) + print("Episode: {}, total numsteps: {}, episode steps: {}, reward: {}".format(i_episode, total_numsteps, episode_steps, round(episode_reward, 2))) if i_episode % 10 == 0 and args.eval == True: state = env.reset() @@ -132,9 +129,8 @@ for i_episode in itertools.count(1): writer.add_scalar('reward/test', episode_reward, i_episode) - test_rewards.append(episode_reward) print("----------------------------------------") - print("Test Episode: {}, reward: {}".format(i_episode, test_rewards[-1])) + print("Test Episode: {}, reward: {}".format(i_episode, round(episode_reward, 2))) print("----------------------------------------") env.close()