anupamagarwal001/amc_allocator_env

docs: polish training notebook submission evidence

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

feat: add reward hacking probe policies

docs: remove uppercase blog duplicate

docs: add reward hacking considerations

docs: add reward hacking considerations

docs: polish training trace heading

docs: polish training trace heading

docs: polish training trace heading

docs: anchor training trace evidence

docs: anchor training trace evidence

docs: use svg trained behavior visual

docs: use svg trained behavior visual

docs: use svg trained behavior visual

docs: add trained behavior evidence

docs: add trained behavior evidence

docs: add trained behavior evidence

docs: add trained behavior evidence

docs: add trained behavior evidence

docs: add trained behavior evidence

docs: add trained behavior evidence

docs: point live app link to playground

docs: point live app link to playground

docs: add judge friendly demo trace

docs: add judge friendly demo trace

docs: add judge friendly demo trace

docs: add judge friendly demo trace

docs: add judge friendly demo trace

docs: polish README visual assets

docs: polish README visual assets

docs: polish README visual assets

docs: polish README visual assets

docs: polish README visual assets

docs: finalize round 2 submission package

docs: finalize round 2 submission package

docs: finalize round 2 submission package

docs: finalize round 2 submission package

docs: finalize round 2 submission package

docs: finalize round 2 submission package

docs: tighten final demo framing

docs: sharpen conflict-resolution submission story