Abstract

We introduce Voyager, the first LLM-powered embodied lifelong learning agent in Minecraft that continuously explores the world, acquires diverse skills, and makes novel discoveries without human intervention. Voyager consists of three key components: 1) an automatic curriculum that maximizes exploration, 2) an ever-growing skill library of executable code for storing and retrieving complex behaviors, and 3) a new iterative prompting mechanism that incorporates environment feedback, execution errors, and self-verification for program improvement. Voyager interacts with GPT-4 via blackbox queries, which bypasses the need for model parameter fine-tuning. The skills developed by Voyager are temporally extended, interpretable, and compositional, which compounds the agent's abilities rapidly and alleviates catastrophic forgetting. Empirically, Voyager shows strong in-context lifelong learning capability and exhibits exceptional proficiency in playing Minecraft. It obtains 3.3x more unique items, travels 2.3x longer distances, and unlocks key tech tree milestones up to 15.3x faster than prior SOTA. Voyager is able to utilize the learned skill library in a new Minecraft world to solve novel tasks from scratch, while other techniques struggle to generalize.

Voyager discovers new Minecraft items and skills continually by self-driven exploration, significantly outperforming the baselines.

Introduction

Building generally capable embodied agents that continuously explore, plan, and develop new skills in open-ended worlds is a grand challenge for the AI community. Classical approaches employ reinforcement learning (RL) and imitation learning that operate on primitive actions, which could be challenging for systematic exploration, interpretability, and generalization. Recent advances in large language model (LLM) based agents harness the world knowledge encapsulated in pre-trained LLMs to generate consistent action plans or executable policies. They are applied to embodied tasks like games and robotics, as well as NLP tasks without embodiment. However, these agents are not lifelong learners that can progressively acquire, update, accumulate, and transfer knowledge over extended time spans.

Let us consider Minecraft as an example. Unlike most other games studied in AI, Minecraft does not impose a predefined end goal or a fixed storyline but rather provides a unique playground with endless possibilities. An effective lifelong learning agent should have similar capabilities as human players: (1) propose suitable tasks based on its current skill level and world state, e.g., learn to harvest sand and cactus before iron if it finds itself in a desert rather than a forest; (2) refine skills based on environment feedback and commit mastered skills to memory for future reuse in similar situations (e.g. fighting zombies is similar to fighting spiders); (3) continually explore the world and seek out new tasks in a self-driven manner.

Kamera Bk Ru Rapidshare -

Having an address like username@bk.ru was a status symbol of the early Russian internet.

People searching for "kamera" were often looking for driver software, firmware updates, or, more commonly, folders of photos and videos uploaded by others. 2. BK.ru: The Mail.ru Ecosystem

Today, searching for this string is mostly an exercise in digital archaeology. RapidShare shut down in 2015, and most links from that era are now "dead."

Instead of generic "kamera" drivers, users now look for Wi-Fi security cameras (some even branded as "BK") that sync directly to smartphone apps.

The "BK" community has largely migrated to VK (VKontakte) , which integrated the file-sharing and "kamera" culture into a single, massive ecosystem. kamera@bk.ru_grozniy-moskva :: video.mail.ru

RapidShare has been replaced by Telegram channels, Yandex Disk, and Google Drive, which offer much higher speeds and security.

If a file was too big for an email (which most "kamera" videos were), you would upload it to RapidShare and post the link on a forum or in an email.

The keyword "" is a relic of the mid-to-late 2000s internet, reflecting a specific era of file sharing, early social networking in Russia, and the rise of digital photography.