Interactive research paper

Realistic evaluation of DRL portfolio claims

An interactive paper on how conclusions from a TD3 model change when evaluated with costs, explicit cash, matched benchmarks and statistical validation.

TD3 case studyCostsCash protocolsMatched benchmarksBootstrapWhite Reality Check

By Luigui Herrera

Published:

Updated:

Evaluation problem

An attractive backtest can create false confidence

Apparent result

A DRL portfolio candidate can rank well after training and produce an attractive backtest.

Conceptual illustration

timevalue

Sources of overstatement

The credibility of the result depends on the evaluation design around the algorithm.

  • Weak or mismatched benchmarks
  • Simplified transaction costs
  • Ambiguous cash treatment
  • Candidate-search bias
  • Limited statistical validation

Therefore, the thesis evaluates the claims around TD3.

Evidence hierarchy

Three increasingly strong claims

Research question

Can a falsification-oriented evaluation framework distinguish ranking competitiveness, statistical credibility and practical feasibility in TD3-based cross-asset portfolio allocation?

Ranking

Performs well against matched benchmarks?

Statistics

Survives uncertainty and data-snooping controls?

Feasibility

Remains plausible under mandates and execution stress?

Interpretive rule

Ranking first does not prove statistical superiority, and statistical superiority would still not guarantee deployability.

Test bed

Asset universe

The universe is deliberately compact. It does not try to represent the whole global market; it creates an interpretable test bed.

SPY

01

Equity / growth risk

Adds growth beta and broad US equity risk.

TLT

02

Duration / interest-rate risk

Adds long-duration Treasury and rate sensitivity.

GLD

03

Real safe-haven / hard-asset exposure

Tests defensive diversification and hard-asset exposure.

BTC-USD

04

Digital alternative / speculative convexity

Adds speculative convexity and extreme volatility.

CASH / BIL

05

Defensive liquidity / optionality

Serves as the defensive sleeve and mandate control.

TD3 mechanism

How TD3 produces portfolio allocations

TD3 is used as a continuous-control learner; the contribution is not a new algorithm variant.

Actor network

Market state
Actor network
Portfolio weights

Twin critics Q1 / Q2

Input [state, action]
Q1
Q2
Lower Q estimate

Evaluation framework

The candidate faces a demanding protocol

Temporal separation and comparison under matching assumptions are part of the test.

  1. 01Data and feature families
  2. 02TD3 candidate training
  3. 03Walk-forward validation and out-of-sample testing
  4. 04Matched deterministic benchmarks
  5. 05Bootstrap uncertainty and White Reality Check
  6. 06Regime, mandate, Pareto, execution and budget diagnostics
Train
Validate
OOS test

Temporal separation is part of the test.

Ranking evidence

Competitiveness survives under matched assumptions

The table compares benchmark-matched TD3 candidates with Trend SPY/CASH, the clean comparator used in statistical validation.

Zero-CASH

Zero-CASH. Max drawdown: -0.1040; Bootstrap CI: [-0.6011, 0.9767]; P(beats): 0.629; WRC p-value: 0.7136.
MetricTD3Trend SPY/CASH
Annualized return: 8.69% 9.79%
Sharpe ratio: 0.923 0.880
Maximum drawdown: -10.4% -17.8%
Selected TD3: V3 clean macro cap 0.70

BIL-CASH

BIL-CASH. Max drawdown: -0.1030; Bootstrap CI: [-0.7172, 0.9963]; P(beats): 0.588; WRC p-value: 0.6767.
MetricTD3Trend SPY/CASH
Annualized return: 10.65% 10.24%
Sharpe ratio: 1.141 0.917
Maximum drawdown: -10.3% -17.3%
Selected TD3: V7 macro+GARCH cap 0.80

Cash treatment changes candidate selection and economic interpretation.

Candidates are selected through diagnostic rankings; economic interpretation relies on standard metrics and statistical validation.

Statistical validation

The intervals do not establish superiority

Bootstrap Sharpe-difference intervals cross zero in both cash protocols.

Bootstrap Sharpe-difference intervals

zeroZero-CASH-0.60110.9767BIL-CASH-0.71720.9963-0.8-0.40.00.40.8Sharpe difference

TD3 remains ranking-competitive, but statistical superiority over the clean benchmark is not established.

The intervals are pairwise evidence; White Reality Check is search-adjusted candidate-set evidence.

Practical feasibility

Execution stress and mandates change the reading

The sensitivity check is post-training: it does not retrain TD3, alter selection or create new winners.

Sharpe degradation under spread stress

Zero-CASH TD3
-0.1321
BIL-CASH TD3
-0.1180
Zero-CASH Trend
-0.0132
BIL-CASH Trend
-0.0132
-0.15-0.10-0.050

Sharpe change · ≈ -0.0132 in the paper

Stress: additional half-spreads of 3/5/5/50/0 bps for SPY/TLT/GLD/BTC-USD/CASH, volatility-adjusted with β = 0.5; post-training sensitivity, with no retraining.

Claim survival

Only some claims survive

The final reading separates competitiveness, statistical inference and practical feasibility.

Only some claims survive
ClaimReadingEvidence boundary
Ranking competitiveness SupportedSelected candidates remain competitive against the matched comparator; return leadership depends on cash.
Statistical superiority Not supportedBootstrap intervals include zero and White Reality Check does not reject.
Cash assumption matters SupportedZero-CASH and BIL-CASH select different candidates.
Execution assumptions matter SupportedTD3 histories degrade more under spread stress.
Conservative mandate feasibility Not supportedNo strategy passes every conservative hard filter.
Pareto competitiveness ConditionalCandidates sit on or near relevant frontiers, depending on profile and trade-off.
Deterministic benchmarks remain credible SupportedTrend SPY/CASH remains a strong clean comparator.

Methodological contribution

From an attractive backtest to a defensible claim

TD3 is the case study; the falsification-oriented evaluation framework is the contribution.

Attractive backtest
Matched evaluation
Bootstrap + WRC
Defensible research claim
Feasibility filters
Defensible research claim
  • Explicit cash treatment
  • Transaction costs
  • Matched deterministic benchmarks
  • Bootstrap uncertainty
  • Data-snooping control
  • Practical feasibility filters

The contribution is methodological rather than algorithmic: it does not propose a new TD3 variant, deployable alpha or universal superiority.

Final answer

01Supported

Ranking competitiveness

Selected TD3 candidates remain competitive against matched deterministic benchmarks on risk-adjusted performance.

02Not established

Statistical superiority

Bootstrap intervals cross zero and White Reality Check does not reject the search-adjusted null.

03Conditional

Practical feasibility

Cash, execution stress, mandates, Pareto trade-offs and market regimes materially affect interpretation.

TD3 is a competitive research candidate for dynamic allocation—not a statistically dominant trading strategy.

Main result: Realistic evaluation materially changes what can responsibly be claimed from favourable DRL portfolio experiments.

Interactive appendix

Methods, limits and traceability

These notes extend the protocol without competing with the main evidence sequence.

Net returns include asset-specific costsOpenClose

SPY, TLT and GLD use 2 bps; BTC-USD uses 10 bps; CASH uses 0 bps under Zero-CASH; BIL uses 2 bps under BIL-CASH. Costs affect realized returns and the learning signal.

Cash is not a footnoteOpenClose

Zero-CASH is a synthetic zero-return, zero-cost sleeve. BIL-CASH uses an investable short-term Treasury proxy. They are different investable environments and are evaluated separately.

TD3 candidate design and feature familiesOpenClose

The search evaluates V2-V8 families, including clean macro, GARCH-style volatility, no-volatility ablations and EWMA/GARCH combinations. PCA was audited but is not the default representation.

Candidate search is controlled by protocolOpenClose

The search combines feature families, caps, seeds, folds and cash. TD3-only selection is separated from benchmark-comparison selection.

Diagnostic selection scoreOpenClose

Mandate-aware and robust scores are diagnostic summaries. They are not superiority tests, calibrated probabilities or proof of deployability.

Benchmark familiesOpenClose

The set includes buy-and-hold, equal weight, 60/40, defensive rules, momentum, rolling Markowitz, minimum variance, inverse volatility and Trend SPY/CASH under matching assumptions.

Walk-forward evaluationOpenClose

Candidates are trained only inside each training window and read out of sample. Four temporal folds reduce dependence on one split but do not create independent market histories.

Bootstrap and White Reality CheckOpenClose

Bootstrap quantifies pairwise uncertainty in the Sharpe difference. WRC provides search-adjusted candidate-set evidence. Neither replaces economic interpretation.

TD3 internal update loopOpenClose

The actor proposes continuous actions; two critics estimate value; target networks, smoothing and delayed updates seek to reduce instability and overestimation.

Reward designOpenClose

Reward begins with net return and includes an active drawdown penalty. Turnover is penalized economically through costs; concentration is evaluated outside the reward.

Feasible-action projectionOpenClose

The raw action is projected onto the simplex: non-negative weights that sum to one. The same feasible action is executed and stored for learning.

Regime analysisOpenClose

TD3 leads selected Zero-CASH slices, while benchmarks and momentum rules win many regimes, especially under BIL-CASH. There is no all-weather dominance.

Mandate filtersOpenClose

Conservative, moderate and aggressive profiles apply drawdown, volatility, effective-diversification and turnover limits. No strategy passes the conservative hard-filter layer.

Training-budget convergenceOpenClose

The check compares 30, 60, 100 and 150 episodes. It finds no obvious undertraining at 60 episodes but does not prove global budget optimality.

Scope limitsOpenClose

The universe is compact and US-centric. It excludes credit, real estate, broad commodities, international equities, taxes, market impact, liabilities and withdrawal needs.

Execution limitsOpenClose

Execution modeling is approximate: it does not model order-book depth, market impact, intraday liquidity, broker routing, custody or taxes.

ReproducibilityOpenClose

The paper documents data, environment, training, benchmark, statistical-validation and robustness scripts. Traceability supports inspection and replication; it does not replace live-forward evidence.

Project repository

Code, scripts and reproducible evidence for the TD3 protocol.