AGENTS

→ View original post on X — @ylecun

World Models and Planning: A Long-Standing AI Research Call

By

@ylecun

–

23 November 2023 18h36

Thanks.
My call for world models and planning goes back a long time.
A good example is my NeurIPS 2016 keynote (slide 31 on). https://
drive.google.com/file/d/0BxKBnD
5y2M8NREZod0tVdW5FLTQ
…

→ View original post on X — @ylecun

Top AI Labs Race to Add Planning Reasoning Capabilities

By

@ylecun

–

23 November 2023 18h10

No.
Everyone in top AI research labs is working on giving dialog systems the ability to plan & reason.
There are projects along those lines at Meta-FAIR, DeepMind, and OpenAI, with early results (if you follow the literature).
Q* is just one such project among many. The planning

Q-Learning Graph Networks for SAT Solver Branching Heuristics

By

–

23 November 2023 17h58

Can Q-Learning with Graph Networks Learn a Generalizable Branching Heuristic for a SAT Solver? Kurin et al.: https://
arxiv.org/abs/1909.11830 #DeepLearning #QLearning #ReinforcementLearning

A* Search Without Expansions: Deep Q-Networks Heuristics

By

–

23 November 2023 17h38

A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networks Agostinelli et al.: https://
arxiv.org/abs/2102.04518 #ArtificialIntelligence #DeepQNetworks #ReinforcementLearning

MetaLearning Enables AI Agents Rapid Adaptation to New Environments

By

–

23 November 2023 16h53

[ MetaLearning.eth ] METALEARNING enables #AIAgents to “learn to learn”, allowing them to rapidly adapt to new environments. Asset: https://
opensea.io/assets/ethereu
m/0x57f1887a8bf19b14fc0df6fd9b2acc9af147ea85/28653756243418125983896305525248630918490602894709024564651983387428933128798
… http://
MONTREAL.AI: Winning the #AGI Race MetaLearning.Eth #MetaLearning #MontrealAI

Reinforcement Learning Powers Web3 AGI Agents Development

By

–

23 November 2023 16h11

[ ReinforcementLearning.Eth ] Reinforcement Learning (RL) is an area of AI concerned with how agents ought to take actions. http://
MONTREAL.AI is using RL to build Web3 AGI Agents Asset: https://
opensea.io/assets/ethereu
m/0x57f1887a8bf19b14fc0df6fd9b2acc9af147ea85/52694602869859807677039526017970231478273063181431708212743385155471956296026
… #ReinforcementLearning

→ View original post on X — @character_ai

Character.AI Helps Navigate Awkward Family Holiday Conversations

By

@character_ai

–

23 November 2023 4h52

Need to get out of those awkward family conversations this holiday season? http://
C.AI HAS GOT YOU! https://
beta.character.ai/chat?char=rhg9
UdB40oTfg4V9TRdHnmZcIJQorEkV1TN-sK_b1Ww
… #CharacterAI