📚 node [[return]]

return

Go back to the [[AI Glossary]]

#rl

In reinforcement learning, given a certain policy and a certain state, the return is the sum of all rewards that the agent expects to receive when following the policy from the state to the end of the episode. The agent accounts for the delayed nature of expected rewards by discounting rewards according to the state transitions required to obtain the reward.

$$\text {Therefore, if the discount factor is } \lambda \text{, and } r_o,\ldots,r_n \text{ denote the rewards until the end of the episode, then the return calculation is as follows:} $$ The equation for return

📖 stoas
⥱ context
⥅ related node [[2003 12 17 return of the awesome]]
⥅ related node [[2006 06 11 socialtext is going open source the return of jluster]]
⥅ related node [[extreme heat in the worlds oceans passed the point of no return in 2014]]
⥅ related node [[online platforms should return value to the citizen body]]
⥅ related node [[20200607142108 roberts_returning_to_normal]]