vlabki/rr-speed-item-v2

Self-contained recurrent player-policy checkpoint.

• Source directory: last
• PPO update: 3000
• Environment steps: 18432000
• Action support: bc

Evaluation values below come from deterministic fixed-seed argmax runs. Frame averages exclude DNF races.

Best reliable evaluation

No completed fixed-seed evaluation recorded.

Best fastest evaluation

No completed fixed-seed evaluation recorded.

Files

Runtime weights, model config, normalization statistics, route reference, training config, and portable checksummed fallbacks are included. Raw rollout traces, optimizer state, and full training logs are excluded.