- Published on
Autonomous AI Agents Launchpad: Research, Frameworks, Tools
Intro
Autonomous AI agents are intelligent entities capable of making decisions and taking actions in complex environments without human intervention. These agents are powered by machine learning techniques, such as reinforcement learning, which enables them to learn from their experiences and adapt their behavior over time.
Reinforcement learning is a unique approach to machine learning where agents learn by trial and error, receiving feedback in the form of rewards or penalties for their actions. This powerful learning paradigm has been instrumental in achieving breakthroughs in various domains, from game-playing AI to robotics and beyond.
In this blog post, you will find a list of resources regarding autonomous AI agents. Research, github repositories, programming libraries, and results of reinforcement learning, autonomous ai agents and large language models, and discussing their potential impact on the future of AI. Please email [email protected] if you would like to add something to this list.
Use AI Agents with UI
Research
WebGPT: Browser-assisted question-answering with human feedback
Duke University Agent Architectures
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
Improving alignment of dialogue agents via targeted human judgements
Sparks of Artificial General Intelligence: Early experiments with GPT-4
Training Language Models with Language Feedback at Scale
Language Models can Solve Computer Tasks
Generative Agents: Interactive Simulacra of Human Behavior
CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society
REACT: SYNERGIZING REASONING AND ACTING IN LANGUAGE MODELS
Reflexion: an autonomous agent with dynamic memory and self-reflection
Principled Reinforcement Learning with Human Feedback from Pairwise or K-wise Comparison
SELF-REFINE:ITERATIVE REFINEMENT WITH SELF-FEEDBACK
SELF-INSTRUCT: Aligning Language Model with Self Generated Instructions