settinghead / rl-chat Public

Experiments on Reinforcement Learning (Policy Gradient)-powered chatbot.

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 208 Commits
bert_yo		bert_yo
data/twitter		data/twitter
dataset		dataset
transformer		transformer
.gitignore		.gitignore
README.md		README.md
agent.py		agent.py
beam_search.py		beam_search.py
conv.txt		conv.txt
conv1.txt		conv1.txt
conv2.txt		conv2.txt
conv3.txt		conv3.txt
corpus_utils.py		corpus_utils.py
data.py		data.py
download_glove.sh		download_glove.sh
embedding_utils.py		embedding_utils.py
encoder_decoder.py		encoder_decoder.py
env_sentiment_stanford.py		env_sentiment_stanford.py
env_sentiment_wordvec.py		env_sentiment_wordvec.py
environment.py		environment.py
environment_CoreNLP.py		environment_CoreNLP.py
pg_update.py		pg_update.py
pg_update_tpu.py		pg_update_tpu.py
play.py		play.py
play_withSent.py		play_withSent.py
poster_plots.ipynb		poster_plots.ipynb
requirements.txt		requirements.txt
seq2seq.py		seq2seq.py
seq2seq_xc.py		seq2seq_xc.py
test_model.py		test_model.py
train_seq2seq.py		train_seq2seq.py
train_seq2seq_leah_test.py		train_seq2seq_leah_test.py
utils.py		utils.py