A3C-Doom fixed one-hot def to work with a_size

awjuliani / DeepRL-Agents

A set of Deep Reinforcement Learning Agents implemented in Tensorflow.

MIT License

2.24k stars 826 forks source link

A3C-Doom fixed one-hot def to work with a_size #25

Closed DMTSource closed 7 years ago

DMTSource commented 7 years ago

Setting a_size to a new value would eventually create an error due to the hard coded(line 230) one-hot array of actions. Replaced with numpy identity using a_size and resolved to a list to match the original format.

awjuliani commented 7 years ago

Thanks for making this fix!