Downloads · 30 days
266
3% of all-time downloads
graceesthi/ug-cppo-finai-2025
ug-cppo-finai-2025 is a reinforcement learning model from graceesthi. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for stable-baselines3. The card lists the license as mit.
Trained models for the UG-CPPO paper v3 (FinAI Contest 2025, NeurIPS 2026 submission).
Downloads · 30 days
266
3% of all-time downloads
All-time downloads
10.4K
Public
Repo size
812 KB
Likes
0
Public
Click a slice to open those files.
.zip8.1 MB · 94%
From the Hugging Face model README
Trained models for the UG-CPPO paper v3 (FinAI Contest 2025, NeurIPS 2026 submission).
Author — Grace-Esther Dong · Aivancity Paris-Cachan Paper —
UG_CPPO_preprint_PAT_corrected.pdfCode — https://github.com/graceesthi/ug_cppo Preprint — arXiv [TBA]
30 trained Stable-Baselines3 agents (10 seeds × 3 algorithms):
{mode}_seed{seed}.zip
ppo_seed42.zip → Vanilla PPO, seed 42
cppo_seed42.zip → CVaR-PPO, seed 42
ug_cppo_seed42.zip → UG-CPPO (ours), seed 42
... (3 modes × 10 seeds = 30 files total)
Cumulative Return (mean ± std)
| Model | Mean | Std | Rachev | MDD | Wilcoxon p (vs PPO) |
|---|---|---|---|---|---|
| PPO | 43.94% | ±32.18% | 0.9445 | −27.95% | — |
| CPPO | 39.71% | ±46.01% | 0.9408 | −31.08% | 0.1720 |
| UG-CPPO | 35.99% | ±38.70% | 0.9420 | −29.72% | 0.8127 |
Interpretation:
Top performers (by Rachev):
from stable_baselines3 import PPO
from huggingface_hub import hf_hub_download
# Download UG-CPPO seed 47 (top performer)
path = hf_hub_download(
repo_id="graceesthi/ug-cppo-finai-2025",
filename="ug_cppo_seed47.zip"
)
agent = PPO.load(path)
ppo_seed*.zip, cppo_seed*.zip, ug_cppo_seed*.zip — Trained agentsmultiseed_report_v13.json — Full results with Wilcoxon testsUG_CPPO_paper.pdf — Full paper with methodologymultiseed_performance.png — Performance comparison plot@inproceedings{dong2026ugcppo,
title={UG-CPPO: Uncertainty-Gated LLM Infusion for Risk-Sensitive
Reinforcement Learning Trading Agents},
author={Dong, Grace-Esther},
booktitle={NeurIPS 2026 — FinAI Contest 2025, Task 1},
year={2026},
note={v3: multi-seed honest evaluation with PAT corrections}
}