smq/directoryAn evolving quant resource archive
Back to directoryResource
Paper / 2025SMQ / 52612187647874
Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards
Caglar Gulcehre / Daniil Karzanov / Marcin Detyniecki / Mikhail Terekhov / Rubén Garzón / Thomas Raffinot
deep learning / portfolio optimizationResource overview

Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards

Paper2025

by Caglar Gulcehre, Daniil Karzanov, Marcin Detyniecki, Mikhail Terekhov, Rubén Garzón, Thomas Raffinot

Tags
deep learningportfolio optimizationreinforcement learningtransaction costs

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

From the same author

Caglar Gulcehre, Daniil Karzanov, Marcin Detyniecki, Mikhail Terekhov, Rubén Garzón, Thomas Raffinot

1