#br
|[[A>#kwA]]|[[B>#kwB]]|[[C>#kwC]]|[[D>#kwD]]|[[E>#kwE]]|[[F>#kwF]]|[[G>#kwG]]|[[H>#kwH]]|[[I>#kwI]]|[[J>#kwJ]]|[[K>#kwK]]|[[L>#kwL]]|[[M>#kwM]]|[[N>#kwN]]|[[O>#kwO]]|[[P>#kwP]]|[[Q>#kwQ]]|[[R>#kwR]]|[[S>#kwS]]|[[T>#kwT]]|[[U>#kwU]]|[[V>#kwV]]|[[W>#kwW]]|[[X>#kwX]]|[[Y>#kwY]]|[[Z>#kwZ]]|

* A [#kwA]
:Agent File| Text file where agent script is written.
:Agent Script| Script language to manage the SkyAI's modules.

* D [#kwD]
:DCOB| Discrete action space for the reinforcement learning application to robot control. DCOB is applicable to a large domain, such as humanoid robots.  See [[DCOB (Yamaguchi's website):http://robotics.naist.jp/~akihiko-y/res/dcob.php]] for the detail.

* S [#kwS]
:SkyAI| SkyAI is an open source software library of reinforcement learning methods. 

* R [#kwR]
:Reinforcement Learning| A learning type of machine learning. A problem to compute the behavior that maximizes the sum of ''reward'' (an evaluation of each action) is categorized to a reinforcement learning problem.

:RL| Reinforcement Learning.

Front page   Edit Diff Backup Upload Copy Rename Reload   New List of pages Search Recent changes   Help   RSS of recent changes