{"paper_id":"2511.20678","title":"Cryptocurrency Portfolio Management with Reinforcement Learning: Soft Actor--Critic and Deep Deterministic Policy Gradient Algorithms","authors":["Kamal Paykan"],"paper_date":"2025-11-16","paper_type":"perspective-policy","paper_url":"https://arxiv.org/pdf/2511.20678v1","page_url":"https://thequant.space/flowcharts/cryptocurrency-portfolio-management-with-reinforcement-learn/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a reinforcement learning‑based framework for cryptocurrency portfolio management using the Soft Actor‑Critic (SAC) and Deep Deterministic Policy Gradient (DDPG) algorithms.","quote":"This paper proposes a reinforcement learning--based framework for cryptocurrency portfolio management using the Soft Actor--Critic (SAC) and Deep Deterministic Policy Gradient (DDPG) algorithms.","summary":"This paper proposes a reinforcement learning–based framework for cryptocurrency portfolio management using the Soft Actor–Critic (SAC) and Deep Deterministic Policy Gradient (DDPG) algorithms. Traditional portfolio optimization methods often struggle to adapt to the highly volatile and nonlinear…","strategy":"Soft Actor–Critic (SAC) cryptocurrency portfolio agent"},"assumptions":{"status":"available","items":[{"assumption":"Classical financial models often assume normally distributed returns and stationary market conditions.","type":"statistical","stated":"explicit","quote":"Classical financial models often assume normally distributed returns and stationary market conditions—assumptions that are frequently violated in cryptocurrency markets."},{"assumption":"Daily portfolio rebalancing is possible without slippage or market impact.","type":"execution","stated":"implied","quote":"The environment simulates daily portfolio re‑balancing, following the RL interaction loop."},{"assumption":"The reward can be defined as the log‑return of portfolio value.","type":"model","stated":"explicit","quote":"The simplest reward is log‑return: rt+1 = ln ( vt+1 vt )."},{"assumption":"The market data (OHLCV) from yfinance accurately reflects true price movements.","type":"data","stated":"implied","quote":"Daily OHLCV data are obtained using yfinance."}]},"datasets":{"status":"available","items":[{"name":"Four major cryptocurrencies (BTC, ETH, LTC, DOGE) OHLCV data","provider":"yfinance","kind":"market-prices","access":"public","period":"Training: 2016‑2022, Testing: 2023‑2024","universe":"BTC, ETH, LTC, DOGE","quote":"Experiments use four major cryptocurrencies: BTC, ETH, LTC, and DOGE. Daily OHLCV data are obtained using yfinance. The period spans: Training: 2016‑2022, Testing: 2023‑2024.","known_id":"yahoo-finance"}],"known":[],"sample":{"start":"2016","end":"2024","market":"BTC, ETH, LTC, DOGE","asset_class":"crypto","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"A constant cost rate c is applied to the sum of absolute changes in portfolio weights each period.","quote":"Accounting for transaction costs with rate c: Rnet t+1 = Rt+1 −c \\nX i=1 |w(i) t −w(i) t−1|.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A constant cost rate c is applied to the sum of absolute changes in portfolio weights each period.","card_quote":"Accounting for transaction costs with rate c: Rnet t+1 = Rt+1 −c \\nX i=1 |w(i) t −w(i) t−1|.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"Both RL agents outperform the Markowitz MPT benchmark, with SAC delivering the highest risk‑adjusted performance.","kind":"performance","quote":"Both reinforcement learning agents outperform the MPT benchmark, with SAC consistently delivering superior risk‑adjusted performance."},{"finding":"SAC shows smoother convergence, lower tail risk (VaR -0.041248, CVaR -0.057676) and more stable returns compared to DDPG and MPT.","kind":"performance","quote":"SAC, on the other hand, achieves smoother convergence with"},{"finding":"DDPG yields negative mean log return and higher drawdowns, indicating instability in volatile environments.","kind":"negative","quote":"DDPG shows negative mean returns and higher drawdowns, indicating insta‑bility in volatile environments."},{"finding":"The forecasting network used as an auxiliary tool attains approximately 70% prediction accuracy, reflecting market volatility and non‑stationarity.","kind":"predictive-accuracy","quote":"prediction accuracy reaching approximately 70%."}],"reported_performance":{"strategy":"Soft Actor–Critic (SAC) cryptocurrency portfolio agent","sharpe":0.0673,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":176.27,"max_drawdown_pct":null},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":48,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:22:00Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}