FunSearch

6 articles tagged with "FunSearch"

Part 7. TANREN — Atari Bowling, the Lost Campaign That Built the Entry Gate: Weighing a Fight Before Running It Series

Part 7. TANREN — Atari Bowling, the Lost Campaign That Built the Entry Gate: Weighing a Fight Before Running It

On Atari Bowling, TANREN beat R2D2, the human benchmark, and DQN, then hit a ceiling at 74% of the strongest RL. This is the record of establishing — by measurement — that the ceiling was structural to the class of readable reactive code, and of how that loss produced the entry gate that now guards every experiment.

Read →
Part 5. TANREN — Discovering Breakout's Tunnel Strategy on Its Own, and Measuring Exactly Why the Rest Is Out of Reach Series

Part 5. TANREN — Discovering Breakout's Tunnel Strategy on Its Own, and Measuring Exactly Why the Rest Is Out of Reach

In Breakout, evolution discovered the classic tunnel strategy without being taught it and reached about 6.1x the human benchmark. Just as important, the reason it could not reach the strongest RL agents was pinned down by measurement, not speculation — drawing the boundary of what a few dozen readable lines of code can do.

Read →
Part 2. TANREN — 11 Wins to 1 Against Twenty Years of Cache Classics, on the Future of a Production Trace Series

Part 2. TANREN — 11 Wins to 1 Against Twenty Years of Cache Classics, on the Future of a Production Trace

Cache eviction — deciding what to drop when a cache is full — has been studied for more than twenty years. On that ground, a 53-line evolved Python function beats ARC, LIRS, and W-TinyLFU on future segments of Twitter's production traces. This post covers how the first attempt lost by overfitting to one time period, the two-window training that fixed it, and the public code anyone can rerun.

Read →
Part 8. TANREN — The Number I Almost Claimed and Then Withdrew: Atari Freeway and Measurement Honesty Series

Part 8. TANREN — The Number I Almost Claimed and Then Withdrew: Atari Freeway and Measurement Honesty

A score of 31.9 looked like a DQN-beating result — until re-measuring under the published side's exact protocol dropped it to 28.6. This is the record of withdrawing the number, repairing the verifier, and re-running the evolution under the correct protocol to reach 31.2: past the human benchmark and DQN, at 96% of Agent57. An article about evaluation honesty.

Read →
Part 6. TANREN — On Atari Skiing, Deep RL's Hardest Slope, Readable Python Beats Every Published RL Agent Series

Part 6. TANREN — On Atari Skiing, Deep RL's Hardest Slope, Readable Python Beats Every Published RL Agent

On Atari Skiing — where Agent57 needed roughly 78 billion training frames to surpass the human benchmark — about 130 lines of readable Python scored −3310.7 in a held-out evaluation, beating every published RL agent and the human benchmark. Includes the entry gate that estimated the odds before running, the techniques evolution added on its own, and the cost contrast: one day and a few dollars.

Read →
Part 1. TANREN — Atari Pong 21–0, and the Kill-Shot the Loop Found on Its Own Series

Part 1. TANREN — Atari Pong 21–0, and the Kill-Shot the Loop Found on Its Own

How an evolutionary loop — a cheap LLM writing code, scored by a deterministic verifier — reached the theoretical ceiling on Atari Pong (21–0 across 40 games) from nothing but the 128-byte RAM, and discovered a single winning shot without being taught it. Includes the honest protocol and the diagnostic loop that made it work for a few dollars.

Read →