US 10,896,382 B2 · Inverse reinforcement learning by density ratio estimation

Abstract

A method of inverse reinforcement learning for estimating cost and value functions of behaviors of a subject includes acquiring data representing changes in state variables that define the behaviors of the subject; applying a modified Bellman equation given by Eq. (1) to the acquired data: q(x)+gV(y)−V(x)=−ln{pi(y|x))/(p(y|x)} (1) where q(x) and V(x) denote a cost function and a value function, respectively, at state x, g represents a discount factor, and p(y|x) and pi(y|x) denote state transition probabilities before and after learning, respectively; estimating a density ratio pi(y|x)/p(y|x) in Eq. (1); estimating q(x) and V(x) in Eq. (1) using the least square method in accordance with the estimated density ratio pi(y|x)/p(y|x), and outputting the estimated q(x) and V(x).

Claims9

Dependent claims

A computer implemented method of inverse reinforcement learning for estimating cost and value functions of behaviors of a subject, comprising:

acquiring, from the subject, data representing changes in state variables that define the behaviors of the subject;
applying a modified Bellman equation given by Eq. (1) to the acquired data:
q
⁡
(
x
)
+
γ
⁢
⁢
V
⁡
(
y
)
-
V
⁡
(
x
)
=
-
ln
⁢
π
⁡
(
y
❘
x
)
p
⁡
(
y
❘
x
)
,
(
1
)
where q(x) and V(x) denote a cost function and a value function, respectively, at state x, V(y) denotes a value function at state y, and γ represents a discount factor, and p(y|x) and π(y|x) denote state transition probabilities before and after learning, respectively;
estimating a density ratio
π
⁡
(
y
|
x
)
p
⁡
(
y
|
x
)
in Eq. (1);
estimating q(x) and V(x) in Eq. (1) using the least square method in accordance with the estimated density ratio
π
⁡
(
y
|
x
)
p
⁡
(
y
|
x
)
;
and
outputting, to forward reinforcement learning controllers for another subject, the estimated q(x) and V(x),
wherein the method of inverse reinforcement learning predicts a preference in topic of articles that a user is likely to read from a series of articles the user selected in an Internet web surfing, and
wherein said subject is the user, and said state variables that define the behaviors of the subject include topics of articles selected by the user while browsing each webpage.

78 more elements

Dependencies are inferred from the claim text.

Inverse reinforcement learning by density ratio estimation

Life of this patent

Inverse reinforcement learning by density ratio estimation

Life of this patent

Abstract

Claims9