89 curated builds·evidence labeled
COMMUNITY OBSERVED

Jev plays Doom

We love how this doomo doomonstrates real-time intelligence and what can be doon

Overview & Result

Demonstrates Jev controlling an autonomous combat agent in classic DOOM. While a macro planner guides spatial navigation toward exit doors, Jev handles millisecond-level target engagement and dodging reflexes under continuous enemy fire.

How Jev fits in the loop

  1. Sample game state and monster proximity from ViZDoom simulation engine.
  2. Query Jev Choice for instantaneous tactical response [SHOOT, STRAFE_LEFT, STRAFE_RIGHT, ADVANCE].
  3. Execute tactical action in <40ms, dodging projectiles before impact.
  4. Log survival longevity and combat efficiency metrics across game runs.

How to reproduce

  1. Inspect author post and reproduction notes.
  2. Deploy agent loop and bind Jev decision endpoints.
  3. Run test inputs and observe latency and accuracy.

Why this build matters

Showcases dual-system architecture in 3D gaming: slow strategic pathfinding paired with fast tactical reflex execution.

Limitations

  • Community observed build; metrics are author-reported.
  • Requires third-party dependencies as described in source.

Patterns