Using Reinforcement Learning in the Algorithmic Trading Problem

Re:Using Reinforcement Learning in the Algorithmic Trading P... by vecter on Wednesday April 29, 2020 @04:27PM (#23023825)

Zero-sum in wealth, but not zero-sum in utility. Otherwise, people wouldn't trade at all.

[ Parent | on HN ]

Re:Using Reinforcement Learning in the Algorithmic Trading P... by buzzkillington on Wednesday April 29, 2020 @07:15PM (#23025717)

That's not true, it just needs to cost you more to not play than it does to play.

Something like:

    |            | Play | Don't Play |
    |------------+------+------------|
    | Play       |   -5 |        +10 |
    | Don't Play |  -10 |          0 |

[ Parent | on HN ]

Re:Using Reinforcement Learning in the Algorithmic Trading P... by nuclearnice1 on Wednesday April 29, 2020 @09:04PM (#23026427)

Your payoffs are not zero sum.

> In game theory and economic theory, a zero-sum game is a mathematical representation of a situation in which each participant's gain or loss of utility is exactly balanced by the losses or gains of the utility of the other participants.

[ Parent | on HN ]

Re:Using Reinforcement Learning in the Algorithmic Trading P... by buzzkillington on Wednesday April 29, 2020 @09:47PM (#23026657)

Yes? The point is that no one playing has the highest payout for the group[1].

[1] You can change the +10 to +9 if you want to make it the absolute highest total payout.

[ Parent | on HN ]

Re:Using Reinforcement Learning in the Algorithmic Trading P... by nuclearnice1 on Saturday May 02, 2020 @12:33PM (#23052819)

Sorry I don’t follow. Can you elaborate?

[ Parent | on HN ]