fix: correct continuous-action PPO scaling, seeding, and eval defaults; retrain pinned models - #19

Merged

eisDNV merged 10 commits into

mainfrom

fix/ppo-acc-squared

Sep 1, 2026

Commits on Aug 28, 2026

fix(controlled_crane_pendulum): don't crash reset() when no episode has run yet
aleksandarbabicdnv
committed
bce6e90
fix(controlled_crane_pendulum): remove double-scaling of continuous acceleration
aleksandarbabicdnv
committed
7411fdb
fix(ppo_agent): remove second acc-squared instance in do_one_episode()
aleksandarbabicdnv
committed
c8973d8

Commits on Aug 29, 2026

Commits on Aug 30, 2026

Commits on Aug 31, 2026