awjuliani / DeepRL-Agents

A set of Deep Reinforcement Learning Agents implemented in Tensorflow.
MIT License
2.23k stars 825 forks source link

checkGoal() in gridworld.py #66

Open anjany opened 6 years ago

anjany commented 6 years ago

(Ref. line 97 in gridworld.py) Shouldn't the 'done' flag be TRUE when the 'hero' reaches either 'goal' or 'fire'? Currently checkGoal( ) always returns a FALSE 'done' status.