载入中...
搜索中...
未找到
类 | |
| struct | PolicyGraph |
| PolicyGraph public API. 更多... | |
| class | Random |
| Random public API. 更多... | |
函数 | |
| std::size_t | weightCount (std::size_t inputs, std::size_t hidden, std::size_t actions) |
| Weight count. | |
| std::vector< double > | layer (const std::vector< double > &x, const Policy &p, std::size_t offset, std::size_t outputs, bool activate) |
| Layer. | |
| std::vector< double > | softmax (std::vector< double > logits, const Observation &o) |
| Softmax. | |
| std::vector< double > | forward (const Policy &p, const Observation &o) |
| Forward. | |
| Policy | makePolicy (const Config &c) |
| Make policy. | |
| void | train (Policy &p, const Observation &o, std::uint32_t action, double rate) |
| Train. | |
| PolicyGraph | makePolicyGraph (int features, int hidden, int actions, bool training) |
| Make policy graph. | |
函数说明
◆ forward()
|
inline |
Forward.
X.
Softmax.
在文件 Learning.h 第 65 行定义.
引用了 eve::agent::Observation::features, layer, p, second, softmax(), third , 以及 x.
被这些函数引用 eve::agent::infer().
◆ layer()
|
inline |
◆ makePolicy()
Make policy.
在文件 Learning.h 第 77 行定义.
引用了 c, eve::agent::Policy::featureCount, p, random, w , 以及 weightCount().
被这些函数引用 eve::agent::run().
◆ makePolicyGraph()
| PolicyGraph eve::agent::detail::makePolicyGraph | ( | int | f, |
| int | h, | ||
| int | a, | ||
| bool | training | ||
| ) |
◆ softmax()
|
inline |
Softmax.
Probabilities.
在文件 Learning.h 第 53 行定义.
引用了 a, eve::agent::Observation::legalActions , 以及 maximum.
◆ train()
|
inline |
Train.
X.
D 2.
Updates .
Updates .
Updates .
在文件 Learning.h 第 90 行定义.
引用了 action, eve::agent::Observation::features, inputs, layer, offset, p, rate, second, softmax(), start, third , 以及 x.
被这些函数引用 eve::agent::run().
◆ weightCount()
|
inline |