Fetching metadata from the HF Docker repository...
-
Fix checkpoint path + default model to Qwen2.5-0.5B for HF API
-
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired
-
fix: implement Phase 1 core fixes (capability matrix, agent wiring, multi-agent inference, robust observation handling)
-
feat: integrate trained LoRA adapters into inference and server, enabling real multi-agent learning deployment
-
feat: activate full multi-agent pipeline with negotiation, conflict handling, and GRPO training
-
fix: wire interaction/ pipeline, add multi-agent inference, fix GRPO
-
feat: implement task grading module and update inference logging to match strict output format
-
feat: add log_end helper and update task logging format to include task metadata and clamped scores
-
feat: implement episode grader and update inference scoring to enforce strict (0.01, 0.99) bounds
-
submission ready
-
feat: implement dashboard UI and integrate uv dependency management
-
fix: resolve all merge conflicts
-
merge: take round1-submission version for all conflicts
-
feat: LLM agent, Leaflet map, batch step, reward fix, inference all tasks
-
improve: better prompt + fixed grader normalization, score 0.77
-
fix: update HF API URL to router.huggingface.co
-
Round 1 submission — SentinelEnv OpenEnv
-
Revert inference.py to original
-
Fix openenv.yaml, Dockerfile, requirements.txt, README for submission compliance
-
Save local changes before pulling main
-
Restore inference.py from vishal1
-
Add Chathur's files: Dockerfile, README, openenv.yaml, requirements.txt
-
feat: complete SentinelRL environment (models, dynamics, reward, env, inference)
Implements OpenEnv-compliant environment with reset/step/state, reward logic, validation, and testing
