OOD-RL-Bench

What is OOD-RL-Bench?

OOD-RL-Bench is an extensible framework for testing out-of-distribution detectors on anomalies injected into RL trajectories. It scores detectors with…

Released

2026-07-14

Evaluates

General AI, Vision & 3D, cs.LG

Openness

unknown

Importer

Claire Radar

Review status

source-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2607.12523

OOD-RL-Bench paper and code

• Paper https://arxiv.org/abs/2607.12523
• Code https://github.com/ood-rl-bench/ood-rl-bench

Which sources cite OOD-RL-Bench?

• OOD-RL-Bench

Related General AI, Vision & 3D, cs.LG benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ActBench
• ActiveSciBench