Spaces:

SmritiS21
/

AryaX

Sleeping

App Files Files Community

58.2 MB

Ctrl+K

Ctrl+K

7 contributors

History: 137 commits

smiit's picture

Keep mx_obs after episode done, prevent reset_multi first error

53a8778 5 months ago

agent
fix: resolve all merge conflicts 6 months ago
agents
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
checkpoints
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
env
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
interaction
fix: rewards, conflict detection, training comparison panel 5 months ago
logs
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
server
feat: add pyproject.toml, openenv.yaml, server/app.py for validation 6 months ago
static
Default to multi-agent mode on load 5 months ago
tasks
fix: evaluate() uses trained agents, grader uses agent instances in eval loop 5 months ago
templates
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
.gitattributes

1.6 kB
track png with lfs 5 months ago
.gitignore

4.83 kB
feat: add SentinelRL environment files (Vishal) 6 months ago
.hfignore

30 Bytes
exclude checkpoints from hf space 5 months ago
AryaX_train_colab.ipynb

19.2 kB
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
Dockerfile

459 Bytes
Fix API_BASE_URL to correct HF inference /v1 endpoint 5 months ago
README.md

17.2 kB
feat: integrate trained LoRA adapters into inference and server, enabling real multi-agent learning deployment 5 months ago
body.json

41 Bytes
xet

Round 1 submission — SentinelEnv OpenEnv 6 months ago
curriculum.py

9.46 kB
fix: resolve training stagnation by randomizing curriculum seeds and enabling real-time metrics logging 5 months ago
generate_metrics.py

6.69 kB
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
inference.py

19.2 kB
Fix checkpoint path + default model to Qwen2.5-0.5B for HF API 5 months ago
openenv.yaml

3.84 kB
Setup project environment, fixed Python version issues, added venv, installed dependencies, and configured server execution 5 months ago
ours.py

45.5 kB
fix: implement Phase 1 core fixes (capability matrix, agent wiring, multi-agent inference, robust observation handling) 5 months ago
pyproject.toml

776 Bytes
Fix all audit issues: conflict schema, curriculum wiring, density_factor, eval path, dead files removed 5 months ago
requirements.txt

2.25 kB
add lora checkpoints and training updates 5 months ago
server.py

24.1 kB
Keep mx_obs after episode done, prevent reset_multi first error 5 months ago
server_clean.py

28.1 kB
fix: implement Phase 1 core fixes (capability matrix, agent wiring, multi-agent inference, robust observation handling) 5 months ago
server_remote.py

22.9 kB
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
test_integration.py

13.7 kB
Fix LLM multi-agent proposals: agent-type sensor filtering, prompt improvements, debug logging 5 months ago
theirs.py

52.1 kB
fix: implement Phase 1 core fixes (capability matrix, agent wiring, multi-agent inference, robust observation handling) 5 months ago
train.py

10.1 kB
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
train_colab.py

19.9 kB
Merge branch 'main' into chathu01 5 months ago
trainer.py

32.4 kB
Run 3: Qwen2.5-0.5B GRPO 500 steps | reward 0.96→1.75 | conflict 0.375→0.1875 | dashboard chart | agents wired 5 months ago
uv.lock

543 kB
feat: implement dashboard UI and integrate uv dependency management 6 months ago