diff --git a/site/site.org b/site/site.org index 53b8291f..6e87c488 100644 --- a/site/site.org +++ b/site/site.org @@ -2055,6 +2055,7 @@ If you have any ideas or requests, please post to [[https://github.com/ymd-h/cpp - [[https://ymd_h.gitlab.io/cpprb/survey/combined_er/][Combined Experience Replay (CER)]] - [[https://ymd_h.gitlab.io/cpprb/survey/lfiw/][Likelihood-free Importance Weights (LFIW)]] - [[https://ymd_h.gitlab.io/cpprb/survey/parallel/][Parallel Actors and Learners]] +- [[https://ymd_h.gitlab.io/cpprb/survey/maper/][Model-augmented Prioritized Experience Replay (MaPER)]] @@ -2417,7 +2418,7 @@ CLOSED: [2022-02-09 Wed 07:22] :END: ** Overview -Model-augumented Prioritized Experience Replay (MaPER), which was +Model-augmented Prioritized Experience Replay (MaPER), which was proposed by Y. Oh /et al/.[fn:23], extends critic network in order to predict Q-value better. The critic network, Model-augumented Critic Network (MaCN), predicts not only Q-value but also reward and next