Fetching metadata from the HF Docker repository...
-
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired
-
fix: rewards, conflict detection, training comparison panel
-
Fix: task difficulty counts, dashboard legend modal, training metrics, reward curve, /metrics/history endpoint
-
Person 3: unify AryaXEnv mode param + fix evaluate() to use trained agents
-
fix: implement Phase 1 core fixes (capability matrix, agent wiring, multi-agent inference, robust observation handling)
-
Fix all audit issues: conflict schema, curriculum wiring, density_factor, eval path, dead files removed
-
fix: wire multi-agent pipeline end-to-end
-
Fix LLM multi-agent proposals: agent-type sensor filtering, prompt improvements, debug logging
-
feat: implement full multi-agent realism (agent specialization, conflict injection, partial observability, logging, metrics export)
-
fix: wire interaction/ pipeline, add multi-agent inference, fix GRPO
-
Phase 1 & 2: multi-agent core — AryaXEnv, world model, four agents
-
Setup project environment, fixed Python version issues, added venv, installed dependencies, and configured server execution
-
submission ready
-
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
-
Round 1 submission — SentinelEnv OpenEnv
-
feat: add SentinelRL environment files (Vishal)
