the code is not similar with algorithm in paper?

iclavera / learning_to_adapt

Learning to Adapt in Dynamic, Real-World Environment through Meta-Reinforcement Learning

208 stars 49 forks source link

the code is not similar with algorithm in paper? #19

Open hmhuy0 opened 3 years ago

hmhuy0 commented 3 years ago

hi, i can not find replay buffer in your code as algorithm in the paper. furthermore, why the sampling frequency always 1? can you give me more detail why this technique equal or better than the older version? thanks you!