settinghead / rl-chat

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

rl-chat

Building a sentiment-aware chatbot using supervised and deep reinforcement learning.

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

Language:Python 67.0%Language:Jupyter Notebook 29.3%Language:Perl 3.6%Language:Shell 0.1%Language:Shell 0.0%Language:Shell 0.0%