AGENTS

–

25 November 2023 21h15

You mean, cats are trained with ontologies?

A* vs MCTS: Planning Algorithms Explained by FAIR Researcher

By

–

25 November 2023 18h32

Yuandong is one of several folks who have been working on planning at FAIR.
He explains the difference in applicability between A* (search for shortest path in a graph) and MCTS (search in an exponentially growing tree).

Yuandong’s Planning Research Approaches at FAIR

By

–

25 November 2023 18h28

Exactly.
Yuandong has been working on various approaches to planning at FAIR.

→ View original post on X — @dfintelligence

Transformation of tourist customer relationship with AI and LLM

By

@dfintelligence

–

25 November 2023 15h41

We transformed the customer relationship in tourism at @valdisere thanks to our AI assistant solution built at @deeplayerAI. We combined ETL technologies, scalable infrastructure, vector databases with the power of LLM models to

Building and Training World Models for AI Systems

By

–

25 November 2023 15h38

Surely. The question is how to build and train this world model.

→ View original post on X — @montreal_ai

Deep Transformer Q-Networks for Partially Observable Reinforcement Learning

By

@montreal_ai

–

24 November 2023 23h56

Deep Transformer Q-Networks for Partially Observable Reinforcement Learning Kevin Esslinger, Robert Platt, Christopher Amato : https://
arxiv.org/abs/2206.01078 #Transformers #QNetworks #ReinforcementLearning

Planning with Learned World Models in Robotics

By

–

24 November 2023 20h18

Many people had the idea.
Planning is a centerpiece of control engineering, robotics, and "classical" AI.
The question is how to plan with a *learned* world model.
Many people have worked on this since the late 1980s (e.g. Widrow's "truck backer-upper").
There have been many

→ View original post on X — @montreal_ai

AI Agent v4 NFTs: Digital Artifacts for AGI Era Collectors

By

@montreal_ai

–

24 November 2023 18h44

AI Agent 👾 v4

0 % LISTED!!

Catering to the refined tastes of AI art connoisseurs, these coveted artifacts have the potential to mature into the equivalent of the "CryptoPunks" of the #AGIFirst era.

OS: https://t.co/GFLgomX7CZ #MontrealAI #NFT #NFTs pic.twitter.com/jlQjw1R4hD
— MONTREAL.AI (@Montreal_AI) 24 novembre 2023

AI Agent v4 0 % LISTED!! Catering to the refined tastes of AI art connoisseurs, these coveted artifacts have the potential to mature into the equivalent of the "CryptoPunks" of the #AGIFirst era. OS: https://
opensea.io/collection/ai-
agent-v4
… #MontrealAI #NFT #NFTs

→ View original post on X — @andreasklinger

Agents vs LLMs: Comparing Use Cases and Applications

By

@andreasklinger

–

24 November 2023 16h50

i think of them like LLMs
work great for glue-code tasks eg LLM's are great for stuff that's messy to code (eg get data from those random data dumps) eg agents are good for stuff that's messy to explain (eg search and figure out if person is X… i dont care which page)