Return to Question

I am trying to solve for lambda using Temporal Difference Learning I am trying to figure out what lambda I need, to make TD(λ)=TD(1)

but I get the incorrect value of lambda.

Here is how I did:

The expected output is: 0.20550275877409016 but I am getting array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1.])

I am just using TD(λ) for state 0 after one iteration. I am not required to see where it converges, so I don't update the value estimates.

I am trying to solve for $\lambda$ using temporal-difference learning. More specifically, I am trying to figure out what $\lambda$ I need, such that $\text{TD}(\lambda)=\text{TD}(1)$, after one iteration. But I get the incorrect value of $\lambda$.

Here's my implementation.

The expected output is: $0.20550275877409016$, but I am getting array([1., 1., 1., 1., 1., 1., 1., 1., 1., 1.])

I am just using TD($\lambda$) for state 0 after one iteration. I am not required to see where it converges, so I don't update the value estimates.

probToState=0.64, 
valueEstimates={0.0,4.9,7.8,-2.3,25.5,-10.2,-6.5}
rewards={-2.4,9.6,-7.8,0.1,3.4,-2.1,7.9

but I get the incorrect value of lambda.

but I get the incorrect value of lambda.