Pith. sign in

REVIEW

Cross Learning in Deep Q-Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2009.13780 v1 pith:CQZDWXOC submitted 2020-09-29 cs.AI

classification cs.AI
keywords overestimationalgorithmbiascrossdeeplearningq-learningq-networks
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated by function approximation errors. Our algorithm builds on double Q-learning, by maintaining a set of parallel models and estimate the Q-value based on a randomly selected network, which leads to reduced overestimation bias as well as the variance. We provide empirical evidence on the advantages of our method by evaluating on some benchmark environment, the experimental results demonstrate significant improvement of performance in reducing the overestimation bias and stabilizing the training, further leading to better derived policies.

Discussion (0). Sign in to comment.

Pith tools