Selective Credit Assignment

by   Veronica Chelu, et al.

Efficient credit assignment is essential for reinforcement learning algorithms in both prediction and control settings. We describe a unified view on temporal-difference algorithms for selective credit assignment. These selective algorithms apply weightings to quantify the contribution of learning updates. We present insights into applying weightings to value-based learning and planning algorithms, and describe their role in mediating the backward credit distribution in prediction and control. Within this space, we identify some existing online learning algorithms that can assign credit selectively as special cases, as well as add new algorithms that assign credit backward in time counterfactually, allowing credit to be assigned off-trajectory and off-policy.


Hindsight Credit Assignment

We consider the problem of efficient credit assignment in reinforcement ...

Forethought and Hindsight in Credit Assignment

We address the problem of credit assignment in reinforcement learning an...

Theta sequences as eligibility traces: a biological solution to credit assignment

Credit assignment problems, for example policy evaluation in RL, often r...

Predecessor Features

Any reinforcement learning system must be able to identify which past ev...

Credit Crunch: The Role of Household Lending Capacity in the Dutch Housing Boom and Bust 1995-2018

What causes house prices to rise and fall? Economists identify household...

Credit Assignment for Trained Neural Networks Based on Koopman Operator Theory

Credit assignment problem of neural networks refers to evaluating the cr...

Online NEAT for Credit Evaluation – a Dynamic Problem with Sequential Data

In this paper, we describe application of Neuroevolution to a P2P lendin...

Please sign up or login with your details

Forgot password? Click here to reset