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.

- Rangbaaz -2018- Hindi - Complete WEB SERIES -...

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.

- Rangbaaz -2018- Hindi - Complete Web Series -... Jun 2026

As the episodes progress, Shiv’s notoriety expands beyond regional borders. He graduates from local extortion and contract killings to manipulating state-level government tenders, railway contracts, and executing audacious daylight assassinations. The narrative reaches its boiling point when Shiv breaches an unspoken code by accepting a contract to assassinate the Chief Minister of Uttar Pradesh, triggering an unprecedented crackdown by the state's law enforcement. Character Analysis and Performances

is a landmark Indian crime-drama web series that premiered as a ZEE5 Original . Set against the rustic backdrop of Gorakhpur, Uttar Pradesh, during the lawless 1990s, the series chronicles the meteorous rise and inevitable fall of a small-town boy turned dreaded gangster. The show carved out its own unique space by offering a gritty, deeply authentic look at the deadly nexus between local criminals, politicians, and law enforcement. The Plot: A Descent into the Heartland Underworld

At the core of the show’s success is Saqib Saleem’s transformative lead performance, backed by a stellar ensemble cast including Tigmanshu Dhulia, Aahana Kumra, Ravi Kishan, and Ranvir Shorey. The complete web series serves as both a chilling period piece and a cautionary tale about the nexus of crime, politics, and law enforcement. The Genesis of a Gangster: Plot and Narrative Structure

The series captures the "desi" vibe of the 90s perfectly—from the vintage cars and rotary phones to the dusty lanes of Gorakhpur. The dialect and cultural nuances feel genuine, not forced.

As Shiv's love interest, Kumra adds a layer of emotional vulnerability to an otherwise hyper-masculine, violent world.

Shoot locations, heavy dialects, and 90s styling create an immersive experience.

The first season of Rangbaaz works effectively as an origin story, exploring themes of ambition, power, and the cycle of violence. While the storyline is rooted in the familiar Bollywood template of a "boy meets gun, boy becomes don", its strength lies in its grounded setting and strong character work. Director Bhav Dhulia successfully captures the rustic, raw energy of 1990s Uttar Pradesh. A key strength is the show's ability to add to a brutal character. We see his love, his fear, and his vulnerabilities, which makes his eventual downfall impactful, even though the audience knows the inevitable fate of a gangster.

Director Bhav Dhulia and writer Siddharth Mishra deserve immense credit for the authenticity of the series. Recreating the 1990s without relying on caricature is difficult, yet Rangbaaz achieves this through careful attention to detail.