Multi-Indicator A2C for Adaptive Equity Trading

Summary

The document presents QTMRL, a reinforcement learning agent designed to make equity trading decisions using technical indicators. Its input dataset combines daily price and volume data for representative S&P 500 stocks across sectors with features intended to capture trends, volatility, and momentum. An Advantage Actor-Critic framework connects data processing, policy learning, and trading actions, aiming to adapt decisions as market conditions change.

The paper reports comparisons with statistical, neural-network, and moving-average baselines across different market regimes, and claims advantages in profitability, risk-adjusted performance, and downside control. The description does not provide metric values, detailed experimental procedures, transaction-cost assumptions, or evidence about performance beyond the stated sample. The dataset spans a long historical period, but results from those stocks and dates may not generalize to other assets or live trading. The summary therefore supports learning about the system design, while leaving its robustness and deployability unclear.

Key ideas

• The agent combines trend, volatility, and momentum indicators with reinforcement learning.
• Its policy uses an Advantage Actor-Critic framework to select trading actions.
• The input data covers daily observations for selected S&P 500 stocks across several sectors.
• The paper compares the system with statistical, neural, and moving-average baselines.
• Reported performance claims lack numerical results and live-trading evidence in the description.

Tags

# QTMRL: An Agent for Quantitative Trading Decision-Making Based on Multi-Indicator Guided Reinforcement Learning


# QTMRL: An Agent for Quantitative Trading Decision-Making Based on Multi-Indicator Guided Reinforcement Learning









In the highly volatile and uncertain global financial markets, traditional quantitative trading models relying on statistical modeling or empirical rules often fail to adapt to dynamic market changes and black swan events due to rigid assumptions and limited generalization. To address these issues, this paper proposes QTMRL (Quantitative Trading Multi-Indicator Reinforcement Learning), an intelligent trading agent combining multi-dimensional technical indicators with reinforcement learning (RL) for adaptive and stable portfolio management. We first construct a comprehensive multi-indicator dataset using 23 years of S&P 500 daily OHLCV data (2000-2022) for 16 representative stocks across 5 sectors, enriching raw data with trend, volatility, and momentum indicators to capture holistic market dynamics. Then we design a lightweight RL framework based on the Advantage Actor-Critic (A2C) algorithm, including data processing, A2C algorithm, and trading agent modules to support policy learning and actionable trading decisions. Extensive experiments compare QTMRL with 9 baselines (e.g., ARIMA, LSTM, moving average strategies) across diverse market regimes, verifying its superiority in profitability, risk adjustment, and downside risk control. The code of QTMRL is publicly available at https://github.com/ChenJiahaoJNU/QTMRL.git

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.