Spaces:

qpluslab
/

OpenRA-Bench

Running

App Files Files Community

OpenRA-Bench

Ctrl+K

9 contributors

History: 416 commits

yxc20098

fix(scenario): combat-tank-vs-tank-engagement — recalibrate after engine movement fixes

e05ae9b about 2 months ago

.github
Move HF Space sync to openra-rl org 5 months ago
data
Update docs: CLI submission, agent identity, replay downloads, API endpoints 5 months ago
docs
docs: Wave 1 engine-footgun aggregation in CLAUDE.md + regen scenarios.html about 2 months ago
openra_bench
fix(scenario): combat-tank-vs-tank-engagement — recalibrate after engine movement fixes about 2 months ago
playback
win-speed bonus: record + reward how fast a model wins about 2 months ago
scripts
#2: enforce ordered waypoints (stateful waypoint_sequence) + two-path medium + scouted hard about 2 months ago
tests
fix(scenario): combat-tank-vs-tank-engagement — recalibrate after engine movement fixes about 2 months ago
tools
Research-grounded 200-level scenario catalog (12 categories) + integ 2 months ago
.DS_Store

8.2 kB
Bench: consume S9 economy obs + economy win-conditions + full toolset 2 months ago
.gitignore

87 Bytes
Add in-browser evaluation via Evaluate tab 5 months ago
AGENTS.md

387 Bytes
docs: CLAUDE.md + AGENTS.md — pointer for friend's Claude Code / Codex agents to use the no-cheat scenario methodology about 2 months ago
CLAUDE.md

20.2 kB
docs(CLAUDE.md): engine-facts — attack_unit no-teleport + stance-respecting move-fire about 2 months ago
EVAL_STACK_PLAN.md

9.01 kB
Add Rust-backed eval stack: scenario packs, adapter, spine, integration tests 2 months ago
LICENSE

35.1 kB
Initial commit 5 months ago
README.md

3.02 kB
Update docs: CLI submission, agent identity, replay downloads, API endpoints 5 months ago
SCENARIO_AUDIT.md

24.3 kB
Adversarial 1v1 spotlight: ladder family + rating + Elo wiring about 2 months ago
SCENARIO_BACKLOG.md

24.7 kB
schema: add meta.benchmark_anchor (list[str]); + SCENARIO_BACKLOG.md (200-pack catalog) about 2 months ago
SCENARIO_BRAINSTORM.md

20.8 kB
tech-production-planning pack: canonical Family 2 (Sequential Dependency Planning) about 2 months ago
SCENARIO_CATALOG.md

8.35 kB
Curate: remove the auto-generated cat-* corpus about 2 months ago
SCENARIO_QUALITY.md

34 kB
docs: whole-suite no-cheat pass summary + engine footguns; regenerate catalog about 2 months ago
SCENARIO_REVIEW.md

12.6 kB
docs: SCENARIO_REVIEW.md — prioritized improvement plan with LOE (#7) about 2 months ago
SCENARIO_REVIEW_CHECKLIST.md

7.41 kB
docs: per-scenario closer-look checklist distilled from #1 and #2 about 2 months ago
app.py

46.2 kB
Training-parity minimap (real terrain + legend) + viewer (system/thinking/debrief) about 2 months ago
eval_stats.json

1.64 kB
win-speed bonus: record + reward how fast a model wins about 2 months ago
evaluate.py

8.52 kB
Add minimum game count, difficulty multiplier, and updated scoring formula 5 months ago
evaluate_runner.py

6.29 kB
Add minimum game count, difficulty multiplier, and updated scoring formula 5 months ago
r_amc_easy.json

1.56 kB
prompt_v2: sanitize confusing 'Buildings: ? ()' briefing line about 2 months ago
r_amc_medium.json

1.57 kB
prompt_v2: sanitize confusing 'Buildings: ? ()' briefing line about 2 months ago
requirements.txt

89 Bytes
Fix CI: add openra-rl-util to requirements.txt 5 months ago
rubrics.py

389 Bytes
Fix scoring dedup, add test suite, wire openra-rl-util 5 months ago
smoke_qwen.json

1.79 kB
prompt_v2: sanitize confusing 'Buildings: ? ()' briefing line about 2 months ago