RL agent beats Pokémon Red with a <10M-parameter policy, 60,500x smaller than DeepSeek-V3

Bam4d · x · 2026-11-17

A project running since 2020 beat Pokémon Red with reinforcement learning using a <10M parameter policy (60,500x smaller than DeepSeek-V3) with minimal simplifications. All code is open sourced. The team argues JRPGs make excellent RL benchmarks: Go/StarCraft-level complexity, nonlinear, >24h gameplay, multi-task reasoning and non-obvious rewards. The output is a technique, not just a policy, with a changelog and Discord community.

Original post →

More from Research

Research channel →