The Home for Artificial Intelligence on the Web
If you thought the hype for artificial intelligence was off the charts, I think in a few years you’ll be shocked at the hype around quantum computing. If you’re unfamiliar with it, quantum computing is a novel computing paradigm where computers exploit novel quantum effects to get exponential speed ups in certain tasks. In particular, [ ]
In a recent post I wrote about how artificial intelligence, and more specifically a reinforcement learning agent, was able to optimize sorting algorithms writing assembly code. This hints at using AI to write entirely novel viruses and malware agents from scratch. Fortunately for us, this is an extremely expensive (compute and development) proposition. Unfortunately, [ ]
I m a little late getting to this paper, seeing as it came out a couple years ago, but I figured it still relevant given the rapid acceleration of the decline of the west. New ideas are desparately needed, and perhaps this paper can yield some fruitful discussion that can, at the very least, slow down [ ]
Deep Mind Astonishes Again Lost in all the excitement for the new wave of large language models was a paper published in Nature, the big brains over at Deep Mind. It s really staggering that we live in a time where an assembly writing AI is barely a blip on the radar, but here we [ ]
Scope of the task I’ve recently started to touch on various on-going approaches to artificial general intelligence. I think the field of AI has started to reach an inflection point where we can start to have these sorts of discussions with some degree of credibility. While I recently came out in support of the [ ]
One of the largest benefits of having a YouTube channel is that people occasionally reach out to me to work on really great projects. Perhaps the coolest opportunity to come along was when a researcher named Chris Poulin contacted me to help him with an implementation of Deep Mind s Agent57. For those that don t know, [ ]
Along with the use of target networks, replay memory stands out as one of the most impactful innovations in deep reinforcement learning. Replay memory has been successfully deployed in both value based and policy gradient based reinforcement learning algorithms, to great success. The reasons for this success cut right to the heart of reinforcement learning. [ ]
Policy gradient and actor critic algorithms remain our only real tool for designing agents to interact with environments with continuous action spaces. Other popular value based algorithms, such as Deep Q Learning, simply aren t suited for dealing with continuous action spaces. Sure, a clever engineer could discreteize the action space, but this would introduce a [ ]
Deep reinforcement learning saw an explosion in the mid 2010s due to the development of the deep q learning (DQN) algorithm. DQN’s success was driven the use of multiple innovations. Perhaps the most important being the use of experience replay for updating deep neural networks . While this was a breakthrough in the field, [ ]
This article is for those of us who have gotten stuck implementing an experience replay buffer as a beginner. That includes me. I see a lot of DRL agent implementations online using experience replay buffers made out of a bunch of numpy arrays. This data strategy isn t new, and there s a reason it runs nice [ ]