-
Directly Estimating the Variance of the λ-Return Using Temporal-Difference Methods
This paper investigates estimating the variance of a temporal-difference...
read it
-
Beyond Exponentially Discounted Sum: Automatic Learning of Return Function
In reinforcement learning, Return, which is the weighted accumulated fut...
read it
-
Parametric Return Density Estimation for Reinforcement Learning
Most conventional Reinforcement Learning (RL) algorithms aim to optimize...
read it
-
Off-policy Multi-step Q-learning
In the past few years, off-policy reinforcement learning methods have sh...
read it
-
Return to Bali
This paper gives an overview of the project Return to Bali that seeks to...
read it
-
Simulating an infinite mean waiting time
We consider a hybrid method to simulate the return time to the initial s...
read it
-
Mixture of Step Returns in Bootstrapped DQN
The concept of utilizing multi-step returns for updating value functions...
read it
Incrementally Learning Functions of the Return
Temporal difference methods enable efficient estimation of value functions in reinforcement learning in an incremental fashion, and are of broader interest because they correspond learning as observed in biological systems. Standard value functions correspond to the expected value of a sum of discounted returns. While this formulation is often sufficient for many purposes, it would often be useful to be able to represent functions of the return as well. Unfortunately, most such functions cannot be estimated directly using TD methods. We propose a means of estimating functions of the return using its moments, which can be learned online using a modified TD algorithm. The moments of the return are then used as part of a Taylor expansion to approximate analytic functions of the return.
READ FULL TEXT
Comments
There are no comments yet.