Model card
Agent57.
DeepMindopen-sourceDistributed RL (Recurrent + Episodic Memory)
First agent to surpass human performance on all 57 Atari games. Uses a meta-controller to adapt exploration.
§ 01 · Benchmarks
Every benchmark Agent57 has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Atari 2600 | Reinforcement Learning · Atari Games | human-normalized-score | 4731.30 | #3 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where Agent57 actually performs.
§ 04 · Related models
Other DeepMind models scored on Codesota.
§ 05 · Sources & freshness
Where these numbers come from.
deepmind-research
1
result
0 of 1 rows marked verified.