Q：Implementing Eligibility Traces in SARSA
I am writing a MATLAB implemention of the SARSA algorithm, and have successfully writtena one-step implementation.
I am now trying to extend it to use eligibility traces, but the results I obtain are worse than with one-step. (Ie: The algorithm converges at a slower rate and the final path followed by the agent is longer.)
Essentially, my q-values are stored in an nXm weights matrix where n = number of actions and m = number of states. Eligibility trace values are stored in the e_trace matrix. According to whether I want to use one-step or ET I use either of the two definitions of dw. I am not sure where I am going wrong. The algorithm is implemented as shown in here: http://webdocs.cs.ualberta.ca/~sutton/book/ebook/node77.html
Defines the weight change for all weights in the network (Ie: The change in value for all Q(s,a) pairs), which is then fed into the network adjusted by the learning-rate.
I should add that initially my weights and e-values are set to 0.
基本上，我的Q值都存储在一个N×M个权值矩阵n =动作和状态的M =号。资格迹值存储在e_trace矩阵。根据我是否想用一步或等我用两种数据仓库定义。我不知道我哪里出错了。该算法是显示在这里实现：HTTP：/ / webdocs。CS。ualberta。钙/ ~萨顿/书/电子书/ node77.html
Defines the weight change for all weights in the network (Ie: 这个 change in value for all Q(s,a) pairs), which is then fed into the network adjusted by the learning-rate.
|algorithm matlab sarsa|