News for hackers. Stuff that matters.

A comment on Permutation-Invariant Neural Networks for Reinforcement Learning.

Re:Permutation-Invariant Neural Networks for Reinforcement L... by LudwigNagasena on Saturday November 27, 2021 @09:59PM (#29365798)
> Reinforcement learning agents typically perform poorly if provided with inputs that were not clearly defined in training. A new approach enables RL agents to perform well, even when subject to corrupt, incomplete, or shuffled inputs.

I am not a specialist in NN and the article doesn’t even mention it, but shouldn’t input dropout and input corruption help with this?

[ Parent | on HN ]
Re:Permutation-Invariant Neural Networks for Reinforcement L... by brrrrrm on Saturday November 27, 2021 @10:25PM (#29365928)
From a description in the referenced NeurIPs spotlight paper (https://attentionneuron.github.io)

> While it is possible to acquire a quasi-PI agent by training with randomly shuffled observations and hope the agent’s policy network has enough capacity to memorize all the patterns, we aim for a design that achieves true PI even if the agent is trained with fix-ordered observations.

[ Parent | on HN ]