skills/smithery.ai/reward-function-v330

reward-function-v330

Installation
SKILL.md

Reward Function v3.3.0 - Risk-Aware Composite Reward

Overview

Item Details
Date 2025-01-21
Goal Fix reward hacking and P&L gradient saturation
Files alpaca_trading/gpu/vectorized_env.py, alpaca_trading/gpu/ppo_trainer_native.py
Status Success

Context

v2.5.0 introduced trading_incentive (+0.02 for non-HOLD actions) to fix HOLD bias. However, this created the opposite problem: reward hacking via overtrading.

Additional issues:

  • Direction weight (40%) dominated despite being binary (+1/-1)
  • P&L weight (25%) too low despite being the actual objective
  • P&L saturated via tanh(pnl * 10) - destroyed gradient signal beyond ±0.1% moves
  • Exploration was limited due to low entropy coefficient (0.005)
Installs
2
First Seen
Mar 30, 2026
reward-function-v330 from smithery.ai