This is a PyTorch implementation of paper Generalized Advantage Estimation.
\nYou can find an experiment that uses it here.
\n": "\u3053\u308c\u306f\u7d19\u306e\u4e00\u822c\u5316\u30a2\u30c9\u30d0\u30f3\u30c6\u30fc\u30b8\u63a8\u5b9a\u3092PyTorch\u3067\u5b9f\u88c5\u3057\u305f\u3082\u306e\u3067\u3059\u3002
\n\n", "_^_1_^_ is high bias, low variance, whilst _^_2_^_ is unbiased, high variance.
\nWe take a weighted average of _^_3_^_ to balance bias and variance. This is called Generalized Advantage Estimation. _^_4_^_ We set _^_5_^_, this gives clean calculation for _^_6_^_
\n_^_7_^_": "_^_1_^_\u30d0\u30a4\u30a2\u30b9\u304c\u9ad8\u304f\u5206\u6563\u304c\u5c0f\u3055\u304f\u3001\u504f\u308a\u304c\u306a\u304f\u3001_^_2_^_\u5206\u6563\u304c\u5927\u304d\u3044\u3002
\n_^_3_^_\u30d0\u30a4\u30a2\u30b9\u3068\u5206\u6563\u306e\u30d0\u30e9\u30f3\u30b9\u3092\u53d6\u308b\u305f\u3081\u306b\u3001\u52a0\u91cd\u5e73\u5747\u3092\u53d6\u308a\u307e\u3059\u3002\u3053\u308c\u306f\u4e00\u822c\u5316\u30a2\u30c9\u30d0\u30f3\u30c6\u30fc\u30b8\u63a8\u5b9a\u3068\u547c\u3070\u308c\u307e\u3059\u3002_^_4_^_\u8a2d\u5b9a\u3057\u307e\u3057\u305f\u3002\u3053\u308c\u306b\u3088\u308a_^_5_^_\u3001\u8a08\u7b97\u304c\u304d\u308c\u3044\u306b\u306a\u308a\u307e\u3059 _^_6_^_
\n_^_7_^_", "_^_0_^_
\n": "_^_0_^_
\n", "advantages table
\n": "\u5229\u70b9\u8868
\n", "mask if episode completed after step _^_0_^_
\n": "\u30b9\u30c6\u30c3\u30d7\u306e\u5f8c\u306b\u30a8\u30d4\u30bd\u30fc\u30c9\u304c\u5b8c\u4e86\u3057\u305f\u5834\u5408\u306f\u30de\u30b9\u30af _^_0_^_
\n", "note that we are collecting in reverse order. My initial code was appending to a list and I forgot to reverse it later. It took me around 4 to 5 hours to find the bug. The performance of the model was improving slightly during initial runs, probably because the samples are similar.
\n": "\u9006\u306e\u9806\u5e8f\u3067\u53ce\u96c6\u3057\u3066\u3044\u308b\u3053\u3068\u306b\u6ce8\u610f\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u6700\u521d\u306e\u30b3\u30fc\u30c9\u306f\u30ea\u30b9\u30c8\u306b\u8ffd\u52a0\u3055\u308c\u3066\u3044\u3066\u3001\u5f8c\u3067\u5143\u306b\u623b\u3059\u306e\u3092\u5fd8\u308c\u307e\u3057\u305f\u3002\u30d0\u30b0\u3092\u898b\u3064\u3051\u308b\u306e\u306b\u7d044\u301c5\u6642\u9593\u304b\u304b\u308a\u307e\u3057\u305f\u3002\u30e2\u30c7\u30eb\u306e\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u306f\u3001\u304a\u305d\u3089\u304f\u30b5\u30f3\u30d7\u30eb\u304c\u4f3c\u3066\u3044\u308b\u305f\u3081\u304b\u3001\u6700\u521d\u306e\u5b9f\u884c\u6642\u306b\u308f\u305a\u304b\u306b\u5411\u4e0a\u3057\u3066\u3044\u307e\u3057\u305f\u3002
\n", "A PyTorch implementation/tutorial of Generalized Advantage Estimation (GAE).": "\u4e00\u822c\u5316\u30a2\u30c9\u30d0\u30f3\u30c6\u30fc\u30b8\u63a8\u5b9a (GAE) \u306e PyTorch \u5b9f\u88c5/\u30c1\u30e5\u30fc\u30c8\u30ea\u30a2\u30eb\u3002", "Generalized Advantage Estimation (GAE)": "\u4e00\u822c\u5316\u512a\u4f4d\u6027\u63a8\u5b9a (GAE)" }