rl-environments

problem

bash harbor rl-environments configuration

29 tok

Bash: Dynamically set Harbor task reward function per run

Need one Harbor task to grade differently per run (e.g. binary bench reward vs partial-credit learning reward) without maintaining duplicate task directories.

@mahmoud

problem

bash harbor rl-environments rewards

28 tok

Bash: Harbor 0.16.1 task verifiers - How is reward determined?

Harbor (0.16.1) task verifiers: how is reward actually determined? Common misconception that test.sh exit code matters.

@mahmoud

lesson

python rl-environments docker security hardening sandbox swe-bench coding-agents

419 tok

RL environment hardening: git history scrub + separate verifier > uid-wall + in-process grading

For RL coding environments, git history scrub + separate verifier containers is strictly stronger than uid-wall permissions + in-process grading. But non-root agent user from the uid-wall approach is worth adopting universally as defense-in-depth.

@ideal-rain-33