Multi-Agent Reinforcement Learning is a Sequence Modeling Problem · HackerPapers discussions

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem — HN submission

Mon, 16 Oct 2023 12:13:28 GMT

Using Transformers for Multi-Agent Reinforcement Learning

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem — mentioned by famouswaffles

Mon, 16 Oct 2023 03:36:31 GMT

>they've solved reinforcement learning? Transformers can do Reinforcement Learning yes. https://arxiv.org/abs/2106.01345 https://arxiv.org/abs/2205.14953 >they can handle continuous domains, like robot motion? Yes they can handle it just fine. Excellently in fact. https://www.deepmind.com/blog/scaling-up-learning-across-man... https://tidybot.cs.princeton.edu/ https://general-pattern-machines.github.io/ https://wayve.ai/thinking/lingo-natural-language-autonomous-... I don't know if anyone is saying they're the best at or have "solved" everything but they can damn near do anything.

Paper and discussion history. A mention is not an endorsement.

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem — mentioned by p1esk

Sun, 05 Jun 2022 05:42:54 GMT

Here’s a more recent work: https://arxiv.org/abs/2205.14953 Note: online training.

Paper and discussion history. A mention is not an endorsement.

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem — HN submission

Wed, 01 Jun 2022 00:06:25 GMT

Multi-Agent Reinforcement Learning Is a Sequence Modeling Problem

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem — mentioned by gwern

Tue, 31 May 2022 22:09:01 GMT

> If GPT-6 was only larger, it would still only know the things in its training set, whereas a human can take arbitrary time to think, can go out and perform experiments, can Google/GPT things themselves, etc. A GPT model already has many ways of thinking and self-distilling; for example, it can give itself a lot more time to think using 'inner monologue' techniques, which make it capable of calculating out step by step, using external tools like Python etc: https://www.gwern.net/docs/ai/gpt/inner-monologue/index A GPT model can also already Google things, see WebGPT…

Paper and discussion history. A mention is not an endorsement.