People are asking if there are alternatives to RL in RLHF. Yes, imitation with DAGGER (tutorial: https://
ri.cmu.edu/publications/a
n-invitation-to-imitation/
… ). The user provides feedback with corrections, e.g. when the agent says “that” the user tells the agent that instead of saying “that”, it should say “this”.
AGENTS
-
DAGGER: Imitation Learning Alternative to Reinforcement Learning
By
–
-
AI Cover Letter Writer generates drafts from job descriptions
By
–
2. AI Cover Letter Writer
— AI Breakfast (@AiBreakfast) 7 février 2023
Uses preloaded prompts for any job description and generates a solid rough draft into a selected template. pic.twitter.com/Xptz5hBKYY2. AI Cover Letter Writer Uses preloaded prompts for any job description and generates a solid rough draft into a selected template.
-
E3B: New Method for Exploring Complex Variable Environments
By
–
E3B is a method for exploring complex environments which vary across episodes. This work set a new SOTA for MiniHack & reward-free exploration on Habitat in October.
— AI at Meta (@AIatMeta) 7 février 2023
Read the paper ➡️ https://t.co/5oxIf1kDAy
Get the code ➡️ https://t.co/omz9GLkkha pic.twitter.com/elUIs4FIofE3B is a method for exploring complex environments which vary across episodes. This work set a new SOTA for MiniHack & reward-free exploration on Habitat in October. Read the paper https://
bit.ly/3JUCceJ
Get the code https://
bit.ly/3YulsPk -
Google announces Bard, conversational agent based on LaMDA to compete with OpenAI
By
–
AI News: Google has just announced Bard, a conversational agent built on LaMDA, of course to compete with #OpenAI to demonstrate that the company is not behind on these topics. https://blog.google/technology/ai/bard-google-ai-search-updates/ …
-
AI Benefits Evolution: From Limited Use Cases to Practical Applications
By
–
I think that in the past the real benefits of AI were small or not present at all. E.g. you could train a RL agent but what it is for if it can’t be entertaining for player? Anyway, now things are changing.
-
AI Version of Asmongold Interviewed Live on Stream
By
–
Witnessing history. @AtheneLOL is interviewing in a lifestream a AI version of Asmongold (a very popular streamer) This kind of tech will hit mainstream hard.
-
Montreal.AI: AGI Race with Ethereum Agents
By
–
AGI.Eth “…there is no discrimination against robots or humans in the Ethereum ecosystem…” – Ethereum Foundation http://
MONTREAL.AI: Winning the #AGI Race Website (in construction): https://
montreal.ai AGIAgent.Eth | AGINode.Eth #AGI #AGIFirst #MontrealAI -
Community Collaboration to Improve Spanish Language AI Assistant
By
–
Si tenéis curiosidad y queréis colaborar ya, podéis registraros en la web y veréis varias tareas en las que colaborar. Igualmente prepararé un vídeo con instrucciones para alinear a la comunidad hispana para que este asistente hable perfecto español Más instrucciones pronto!
-
Training AI Agents to Navigate Without Vision or Audio
By
–
Training ‘Blind’ Agents – trains an AI agent to navigate purely by feeling its way around; no use of vision, audio, or any other sensing (as in animals). 9 of 11
-
Top ML Papers of the Week: REPLUG, SceneDreamer, FLAN
By
–
Top ML Papers of the Week (Jan 30 – Feb 5): – REPLUG
– SceneDreamer
– The FLAN collection
– Distractability of LLMs
– Blind navigation agents
– Mathematical capabilities of ChatGPT
… 1 of 11