smq/directoryAn evolving quant resource archive
Back to directoryResource
Paper / UndatedSMQ / 109
Learning to Trade via Direct Reinforcement
John Moody / Matthew Saffell
Bellman’s curse of dimensionality / Q-learningResource overview

Learning to Trade via Direct Reinforcement

Paper

by John Moody, Matthew Saffell

Tags
Bellman’s curse of dimensionalityQ-learningRRLS&P 500Sharpe ratioT-billsTD learningasset allocationcurrency tradingdifferential Sharpe ratiodirect reinforcementdownside deviationfinancial time seriesintraday tradinglearning to tradepolicy gradientportfolio optimizationrecurrent reinforcement learningreinforcement learningrisk-adjusted returnssimulationstochastic controltradingtrading systemstransaction costsvalue function

Access resource

Open original source Understand this paper

Continue on SelfMadeQuant

Understand this paper

Suggested foundations for portfolio construction and market microstructure and execution. Specialist prerequisites vary by paper.

Before you read

  1. Eigenvalues and Covariance Matrices

    Understand the covariance structure of portfolio risk.

  2. Constrained and Convex Optimisation

    Read objectives, constraints and optimality conditions.

  3. Order Books

    Read bid, ask, depth and queue-based market state.

  4. Order Flow and Adverse Selection

    Understand why fills and order flow can carry information.

Go further

  1. Mean-Variance Optimisation

    Construct allocations and examine sensitivity to estimated inputs.

  2. Portfolio Constraints

    Turn mathematical weights into feasible portfolio decisions.

  3. Market Impact

    Connect trading speed and size to execution cost.

Explore a related reading path

Lesson links open public previews. Access to full lessons depends on the topic and your membership.

Explore Portfolio Theory and Quantitative Investment Explore Market Microstructure and Execution

Keep exploring

Related resources

More ideas from similar topics.

6