# A Method of Selective Attention for Reservoir Based Agents

arXiv: https://arxiv.org/abs/2502.21229 · HTML: https://mlsanity.com/paper/2502.21229/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods.
- Builds on 2 of its 8 references that are in the map.
- First posted on arXiv 28 Feb 2025.

## Placed in

- Deep reinforcement learning methods / [Deep RL algorithms and representations](https://mlsanity.com/deeprl/deep-rl-algorithms-and-representations/)

## Builds on (most cited first, 2 of 2)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Reservoir Computing for Fast, Simplified Reinforcement Learning on Memory Tasks](https://mlsanity.com/paper/2412.13093/) (2024)

## Built on by (most cited first, 1 of 1)

- [Flexible Prefrontal Control over Hippocampal Episodic Memory for Goal-Directed Generalization](https://mlsanity.com/paper/2503.02303/) (2025)

## Abstract (arXiv)

Training of deep reinforcement learning agents is slowed considerably by the presence of input dimensions that do not usefully condition the reward function. Existing modules such as layer normalization can be trained with weight decay to act as a form of selective attention, i.e. an input mask, that shrinks the scale of unnecessary inputs, which in turn accelerates training of the policy. However, we find a surprising result that adding numerous parameters to the computation of the input mask results in much faster training. A simple, high dimensional masking module is compared with layer normalization and a model without any input suppression. The high dimensional mask resulted in a four-fold speedup in training over the null hypothesis and a two-fold speedup in training over the layer normalization method.