SADHANA14/alphaBetaGamma

updInf

updPolicy

Revert "fixedPolicy"

Update policy.py

fixedPolicy

Revert "changes"

Revert "llmErr"

Revert "fixedErr"

Revert "rectifyErrors"

Revert "fixed"

fixed

rectifyErrors

fixedErr

llmErr

changes

Update inference.py

Sync scoring/clamping changes from OpenTrafficEnv

Update inference.py

Update infence.py

Update env.py

Update reward.py

Update grader.py

Updated env.py

Update reward.py

Update agent/grader.py

Update inference.py

Update inference.py

Update agent/grader.py

Update simulator/env.py

Update agent/reward.py

Modified env.py step rewards to return value between (0,1)

Clamp simulator score to (0,1)

Ignore runs/ and sync reward scoring

Clamp task scores to (0,1) for validator

Add __main__ guard for server.app

Multi-mode deployment: server/app.py, uv.lock

Add pyproject.toml for deployment

Add openenv.yaml for validator

Allow empty reset body

Add checklist env vars to inference

Use Space base URL by default

Use Space URL in README

Update README

Align repo with OpenTrafficEnv

Sync changes from OpenTrafficEnv

updateREADME

Remove emojis from README

Add root/health endpoints

Specify Spaces app port

Add Dockerized traffic env server