upload teammate_generation for ckpt-eval support

upload open_ended_training for ckpt-eval support

upload ego_agent_training for ckpt-eval support

Dockerfile: include ego_agent_training + open_ended + teammate_generation (needed for upload ego eval)

API: HF dataset mirror for leaderboard + ckpts; fix ego_fn obs.get bug

API: fix partner not acting (current_player unwrap + simultaneous-step handler), -w 1 to keep sessions, drop difficulty labels

fix OBL + BC weight_file paths; Flawed description; flag Prolific as LBF-only

Flawed partner: use play_threshold kwarg (not mistake_prob), drop bogus second entry

API: refresh hanabi heuristics (drop weighted rule_based, add cautious/internal, fix flawed_60 key); About/Home wording + card alignment

add jumanji to requirements (LBF + Overcooked need it via envs/__init__.py)

About: JaxAHT citation, drop source-of-truth line

fix gunicorn invocation: single-quote app spec so sh doesn't parse parens

fix CMD: use --factory instead of create_app() (shell was parsing parens as function-def)

UI polish: LBF caps, About page, GitHub nav link, UT orange accent

re-deploy: study.tsx full play.tsx parity + runtime weight download

clean: drop bulk weights (35/35)

drop duplicate h1 in readme

clean up: remove venv/pyc cruft (1635/1635)

clean up: remove venv/pyc cruft (1600/1635)

clean up: remove venv/pyc cruft (1400/1635)

clean up: remove venv/pyc cruft (1200/1635)

clean up: remove venv/pyc cruft (1000/1635)

clean up: remove venv/pyc cruft (800/1635)

clean up: remove venv/pyc cruft (600/1635)

clean up: remove venv/pyc cruft (400/1635)

clean up: remove venv/pyc cruft (200/1635)

deploy: demo viz, prolific study sessions, mini-hanabi, client-eval submit

Add Dockerfile at root for HF Space build

Initial jaxaht-benchmark deployment

initial commit