search

yandexdataschool / AgentNet

Deep Reinforcement Learning library for humans
http://agentnet.rtfd.org/
Other
301 stars 71 forks source link

Optimailty tightening #87

Closed sidorov-ks closed 7 years ago

sidorov-ks commented 7 years ago

Added bare-bones version of optimailty tightening for Q-learning (as described in arXiv:1611.01606)

justheuristic commented 7 years ago

Seems great! Could you please make it follow the same pattern of inputs as the basic qlearning? (to make transition easier)