logs15:See if new RL is working

See if new RL is working

1: What specific output am I working on right now?

• In logs14:Normalize Reward, we fixed reward logic. We want to confirm if it's working.

2: Thinking out loud - e.g. hypotheses about the current problem, what to work on next, how can I verify

Repeat some of the trials we did in logs11:See if RL works with medium model2, and see if we have some changes in avg_reply_len.

3: A record of currently ongoing runs along with a short reminder of what question each run is supposed to answer

• run1: title

4: Results of runs (TensorBoard graphs, any other significant observations), separated by type of run (e.g. by the environment the agent is being trained in)

run1

average_reward became nan and results got messed up.

ばいとおわ！ [0]
[1]← average reply len=1.0 validation loss=146020.7 learning rate 0.1 msec/data=8.3 .../usr/local/lib/python3.6/dist-packages/ipykernel_launcher.py:112: RuntimeWarning: invalid value encountered in true_divide ...............average_reward=nan .INFO:tensorflow:Restoring parameters from model/tweet_large_rl/ChatbotModel-1662 ==== 1662 ==== おやすみ～ [0][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS][SOS] おやすみ～

hparams >{'machine': 'client2', 'batch_size': 64, 'num_units': 512, 'num_layers': 2, 'vocab_size': 5000, 'embedding_size': 256, 'learning_rate': 0.5, 'learning_rate_decay': 0.99, 'use_attention': True, 'encoder_length': 28, 'decoder_length': 28, 'max_gradient_norm': 5.0, 'beam_width': 0, 'num_train_steps': 1560, 'model_path': 'model/tweet_large'} dst {'machine': 'client2', 'batch_size': 64, 'num_units': 512, 'num_layers': 2, 'vocab_size': 5000, 'embedding_size': 256, 'learning_rate': 0.1, 'learning_rate_decay': 0.99, 'use_attention': True, 'encoder_length': 28, 'decoder_length': 28, 'max_gradient_norm': 5.0, 'beam_width': 0, 'num_train_steps': 1560, 'model_path': 'model/tweet_large_rl'}