Agents

Youtube ... Quora ...Google search ...Google News ...Bing News

• Assistants ... Hybrid Assistants ... Agents ... Negotiation ... HuggingGPT ... LangChain
  • ChatGPT Integration
• Python ... Generative AI with Python ... Javascript ... Generative AI with Javascript ... Game Development with Generative AI
• Development ...AI Pair Programming Tools ... Analytics ... Visualization ... Diagrams for Business Analysis
• Generative AI ... OpenAI's ChatGPT ... Perplexity ... Microsoft's Bing ... You ...Google's Bard ... Baidu's Ernie
• Natural Language Processing (NLP) ...Generation ...LLM ...Tools & Services
• Attention Mechanism ...Transformer Model ...Generative Pre-trained Transformer (GPT)
• Game Theory
• Reinforcement Learning (RL)
• Policy
• Policy Gradient (PG)
• Multi-Task Learning (MTL)
• Deep Reinforcement Learning (DRL)
• SMART - Multi-Task Deep Neural Networks (MT-DNN)
• Deep Distributed Q Network Partial Observability
• Distributed Deep Reinforcement Learning (DDRL)
• Asynchronous Advantage Actor Critic (A3C)
• Deep Q Network (DQN)
• Policy vs Plan
• Types of AI Agents | JavaTpoint ... Simple Reflex, Model-based reflex, Goal-based, Utility-based, Learning agents
• Key Research Advances in Building Task-Oriented Dialog Agents | Mariya Yao - TOPBOTS
• MineDojo ... framework built on the popular Minecraft game for embodied agent research
  • MINEDOJO: Building Open-Ended Embodied Agents with Internet-Scale Knowledge | L. Fan, G. Wang, Y. Jiang, A. Mandlekar, Y. Yang, H. Zhu, A. Tang, D. Huang, Y. Zhu, A. Anandkumar ... https://minedojo.org/videos/mineclip_policy_learning.mp4
• Google Tells AI Agents to Behave Like 'Believable Humans' to Create 'Artificial Society' | Chloe Xiang - Vice ... The characters have developed specific routines, such as waking up, taking a shower, cooking breakfast, interacting with their families, then going to work every day... researchers input one paragraph per character into ChatGPT
• Amazon creates a new user-centric simulation platform to develop embodied AI agents | Ingrid Fadelli - TechExplore ... Arena is a new Embodied AI platform, for robotic task completion in simulated environments.
  • GitHub

An intelligent agent is anything which perceives its environment, takes actions autonomously in order to achieve goals, and may improve its performance with learning or acquiring knowledge. An agent has an "objective function" that encapsulates all the IA's goals. Such an agent is designed to create and execute whatever plan will, upon completion, maximize the expected value of the objective function.[2] For example, a reinforcement learning agent has a "reward function" that allows the programmers to shape the IA's desired behavior,[3] and an evolutionary algorithm's behavior is shaped by a "fitness function". - Wikipedia

🤖 Reinforcement Learning (RL) aims to make an agent (our “model”) learn through the interaction with an environment (this can be either virtual or real). RL was firstly developed to adhere to Markov Decision Process (MDP)es. In this ambit, an agent is placed in a stochastic stationary environment and tries to learn a policy through a reward/punishment mechanism. In this scenario, it is proved the agent will converge to a satisfactory policy. However, if multiple agents are placed in the same environment, this condition is no longer true. In fact, before the learning of the agent was only dependent on the interaction between the agent and the environment, now it is also dependent on the interaction between agents

Autonomous GPT

YouTube ... Quora ...Google search ...Google News ...Bing News

• Developers Are Connecting Multiple AI Agents to Make More ‘Autonomous’ AI | Chloe Xiang - Vice ... Auto-GPT
• Auto-GPT | Toran Bruce Richards ... driven by GPT-4, chains together LLM "thoughts", to autonomously achieve whatever goal you set by can prompting itself to complete an objective.
• Task-driven Autonomous Agent Utilizing GPT-4, Pinecone, and LangChain for Diverse Applications | Yohei Nakajima

AutoGPT

YouTube ... Quora ...Google search ...Google News ...Bing News

• What is Auto-GPT? Everything to know about the next powerful AI tool | Sabrina Ortiz - ZDnet ... Auto-GPT can do a lot of things ChatGPT can't do.

AgentGPT

YouTube ... Quora ...Google search ...Google News ...Bing News

• AgentGPT
  • GitHub
• Beyond ChatGPT: AgentGPT is Bringing Autonomous AI To The Browser NOW | Sebastian - Medium
• AgentGPT template | Vercel ... Assemble, configure, and deploy autonomous AI Agents in your browser, using LangChain, OpenAI, AutoGPT and T3 Stack

AgentGPT allows you to configure and deploy Autonomous AI agents. Name your custom AI and have it embark on any goal imaginable. It will attempt to reach the goal by thinking of tasks to do, executing them, and learning from the results

BabyAGI

YouTube ... Quora ...Google search ...Google News ...Bing News

• Auto-GPT and BabyAGI: How ‘autonomous agents’ are bringing generative AI to the masses | Mark Sullivan - Fast Company ... Autonomous agents may mark an important step toward a world where AI-driven systems are smart enough to work on their own, without need of human involvement.

Multi-Agents Reinforcement Learning (MARL)

• Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms | K. Zhang, Z. Yang, and T. Başar

In a similar vein, multi-agent RL also addresses sequential decision-making problems, but with more than one agent involved. In particular, both the evolution of the system state and the reward received by each agent are influenced by the joint actions of all agents. More intriguingly, each agent has its own long-term reward to optimize, which now becomes a function of the policies of all other agents.

• Markov/Stochastic Games
  • Cooperative Setting
  • Competitive Setting
  • Mixed Setting
• Extensive-Form Games

Challenges

Despite a general model with broad applications, MARL suffers from several challenges in theoretical analysis, in addition to those that arise in single-agent RL.

1. Non-Unique Learning Goals - Unlike single-agent RL, where the goal of the agent is to maximize the long-term return efficiently, the learning goals of MARL can be vague at times. ...Indeed, the goals that need to be considered in the analysis of MARL algorithms can be multi-dimensional ... is undoubtedly a reasonable solution concept in game theory, under the assumption that the agents are all rational, and are capable of perfectly reasoning and infinite mutual modeling of agents. However, with bounded rationality, the agents may only be able to perform finite mutual modeling
2. Non-Stationarity - multiple agents usually learn concurrently, causing the environment faced by each individual agent to be non-stationary. In particular, the action taken by one agent affects the reward of other opponent agents, and the evolution of the state. As a result, the learning agent is required to account for how the other agents behave and adapt to the joint behavior accordingly. This invalidates the stationarity assumption for establishing the convergence of single-agent RL algorithms
3. Scalability Issue - To handle non-stationarity, each individual agent may need to account for the joint action space, whose dimension increases exponentially with the number of agents. This is also referred to as the combinatorial nature of MARL
4. Various Information Structures - Compared to the single-agent case, the information structure of MARL, namely, who knows what at the training and execution, is more involved. For example, in the framework of Markov games, it suffices to observe the instantaneous state st , in order for each agent to make decisions

Communication

Youtube search... ...Google search

• Computer Networks
• Attention
• TALISMAN: A multi-agent system for natural language processing | Marie-Hélène Stefanini & Yves Demazeau - Part of the Lecture Notes in Computer Science book series (LNAI,volume 991) ... One of the originalities of this system is the distributed treatment of sentence analysis (as opposed to a classic sequential treatment) and the introduction of linguistic laws which handle the communication between agents, without central control. At the implementation level, the system brings openness to dictionary modification, grammars and strategies of analysis, as well as the necessary mechanisms for the integration of new modules.
• Integrating AI Planning with Natural Language Processing: A Combination of Explicit and Tacit Knowledge | Kebing Jin, Hankz Hankui Zhuo - Cornell University