native env renderGPT-5.5
Codex- Held-out
- 0.918
- Checkpoint
- #005
- Rerun
- 25 steps
Validation-selected checkpoint rerun in the original environment; case return 0.953.
MiniGrid · Core16
Multi-room search with object interaction and memory.
This evidence belongs to the paper-era experiment and is not a guarantee of current package availability.
Each card reruns the validation-selected checkpoint in the original research Environment.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.953.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.951.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
native env renderValidation-selected checkpoint rerun in the original environment; case return 0.000.
Higher is better within this Environment. Raw reward scales are not comparable across tasks.
0.9300.9180.0000.0000.000