Kingpython123 Claim this profile

GRPO alignment algorithm trainer based on OpenRLHF

Real-time prefix cache hit-rate monitoring for vLLM

Sensitivity-AnalysisSystematic LoRA hyperparameter sensitivity analysis

Deep RL Portfolio Optimization: PPO/SAC/DDPG, Transformer networks, market constraints, benchmarks

Enhanced Quantitative Factor Research: stacking ensemble, SHAP, ICIR, Sharpe evaluation

LLM-Infused Deep RL Trading: multi-LLM ensemble, Transformer policy, comprehensive backtest metrics

No description.

No description.

No description.