Algorithm Distillation: grader v2 with belief_accuracy + SFT pipeline ece0bbe InosLihka commited on 12 days ago
iter4: fix the 'constant belief = free reward' bug + 6 other deep issues bb2a9c7 InosLihka Claude Opus 4.7 (1M context) commited on 12 days ago
iter3: align reward with grader + belief-first format + exploration shaping 64d24b3 InosLihka Claude Opus 4.7 (1M context) commited on 12 days ago
env: meta-RL refactor (continuous profiles, action+belief, adaptation grader) ecbe0d8 InosLihka Claude Opus 4.7 (1M context) commited on 13 days ago
Rebuild as Life Simulator: 5 meters, 3 hidden profiles, GRPO training pipeline cc6473a InosLihka Claude Sonnet 4.6 commited on 14 days ago
InosLihka Claude Opus 4.7 (1M context) commited on 