One interesting part of the paper to me is the strategy in Algorithm 5 that is asymptotically optimal and optimal in the minimax sense. Although the strategy is not very original (a small modification of a strategy suggested by Lai), it is a new observation for a strategy to be asymptotically optimal and minimax optimal. However, it should be noted that it is optimal only in the case of two arms, which is a major drawback. The authors are encouraged to improve on this result. This idea is new to the best of my knowledge.

This paper investigates the problem of multi-UAV uniform sweep coverage, where a homogeneous swarm of UAVs must collectively and evenly visit every portion of an unknown environment for a sampling task without having access to their own location and orientation. Random walk-based exploration strategies are practical for such a coverage scenario as they do not rely on localization and are easily implementable in robot swarms. We demonstrate that the Mergeable Nervous System (MNS) framework, which enables a robot swarm to self-organize into a hierarchical ad-hoc communication network using local communication, is a promising control approach for random exploration in unknown environments by UAV swarms. To this end, we propose an MNS-based random walk approach where UAVs self-organize into a line formation using the MNS framework and then follow a random walk strategy to cover the environment while maintaining the formation. Through simulations, we test the efficiency of our approach against several decentralized random walk-based strategies as benchmarks. Our results show that the MNS-based random walk outperforms the benchmarks in terms of the time required to achieve full coverage and the coverage uniformity at that time, assessed across both the entire environment and within local regions.

IBM Watson Assistant (WA), at its core has a basic intent and entity structure. Intents are as minimalist as can be. During the intent creation process, there are two features which aid in the defining of intents. Bot of these features translate into better defined intents, and translates nicely into the JSON export file. Hence the leverage these functions lend to the intent creation process is not lost.

Can machine learning help clean it up? A team of computer scientists spanning the globe think so. They've built a neural network that can seemingly classify tweets into four different categories: normal, aggressor, spam, and bully – aggressor being a deliberately harmful, derogatory, or offensive tweet; and bully being a belittling or hostile message. The aim is to create a system that can filter out aggressive and bullying tweets, delete spam, and allow normal tweets through. The boffins admit it's difficult to draw a line between so-called cyber-aggression and cyber-bullying.

It's been a few years since I was first exposed to reinforcement learning. What got me into it was seeing this video that had trained a neural network to play Mario. As someone who grew up playing Mario, seeing deep learning being applied to something I knew so well seemed to provided the perfect introduction to the topic. Sadly though, the project was written using Torch, and I was still a naive young programmer. I didn't get too far along before the frustrations with learning lua lead me to give up, and just focus on other projects instead.