search

openai / random-network-distillation

Code for the paper "Exploration by Random Network Distillation"
https://openai.com/blog/reinforcement-learning-with-prediction-based-rewards/
881 stars 160 forks source link

requirement baseline / MuJoCo #6

Closed TheCherry closed 6 years ago

TheCherry commented 6 years ago

Is it really necessary that we need the baseline library (including the mojoco framework) for this project? As far as i can see, only the make_pdtype method is really needed, is there an alternative here?

TheCherry commented 6 years ago

OK the newest baselines from github works, just dont have to take the one from pip.