{"paper_id":"2404.12598","title":"Continuous-time Risk-sensitive Reinforcement Learning via Quadratic Variation Penalty","authors":["Yanwei Jia"],"paper_date":"2024-04-19","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2404.12598v1","page_url":"https://thequant.space/flowcharts/continuous-time-risk-sensitive-reinforcement-learning-via-qu/","scores":{"empirical_rigor":3,"math_complexity":8.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes a continuous-time risk-sensitive reinforcement learning framework that adds a quadratic variation penalty to the value process and introduces a risk-sensitive q‑learning algorithm to incorporate risk sensitivity into existing RL methods.","quote":"This paper studies continuous-time risk-sensitive reinforcement learning (RL) under the entropy-regularized, exploratory diffusion process formulation with the exponential-form objective. This characterization allows for the straightforward adaptation of existing RL algorithms developed for non-risk-sensitive scenarios to incorporate risk sensitivity by adding the realized variance of the value process.","summary":"This paper studies continuous-time risk-sensitive reinforcement learning (RL) under the entropy-regularized, exploratory diffusion process formulation with the exponential-form objective. The risk-sensitive objective arises either as the agent’s risk attitude or as a distributionally robust…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The standard assumptions used in ordinary, non‑risk‑sensitive stochastic control problems are adopted.","type":"model","stated":"explicit","quote":"I make the standard assumptions in the ordinary, non-risk-sensitive stochastic control problems (Yong and Zhou, 1999).","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Synthetic data for Merton’s investment problem and linear‑quadratic control experiments","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"5 Applications I illustrate our methods on two applications with synthetic data sets. The number of episodes within each simulation run is 105.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"Risk‑sensitive RL improves finite‑sample performance in the linear‑quadratic control problem compared to non‑risk‑sensitive approaches.","kind":"performance","quote":"I also conduct simulation experiments to demonstrate how risk-sensitive RL improves the finite-sample performance in the linear-quadratic control problem. With suitable values of ϵ, solving the risk-sensitive objective reduces MSE.","support":"full"},{"finding":"With suitable values of the risk‑sensitivity coefficient ϵ, the mean‑squared error of the estimated policy is reduced; overly large |ϵ| harms accuracy.","kind":"statistical","quote":"With suitable values of ϵ, solving the risk-sensitive objective reduces MSE. As ϵ approaches 0, the results get closer to the non-risk-sensitive objective, whereas overly large ϵ (in the absolute value) harms the accuracy.","support":"full"},{"finding":"The optimal choice of ϵ depends on sample size: larger samples favor smaller risk sensitivity.","kind":"theoretical","quote":"Overall, as the sample size increases, the performance get significantly better. The optimal ϵ is between ´5 29 and ´2 when the sample size is small, and is between ´2 and ´1 when the sample size is large.","support":"full"},{"finding":"The proposed algorithm converges for Merton’s investment problem and the impact of the temperature parameter λ on learning behavior is quantified.","kind":"theoretical","quote":"Finally, I prove the convergence of the proposed algorithm for Merton's investment problem and quantify the impact of temperature parameter on the behavior of the learning procedure.","support":"full"},{"finding":"A smaller temperature parameter λ tends to yield lower estimation error in the off‑policy, offline setting.","kind":"performance","quote":"In addition, a smaller temperature parameter λ seems to induce an overall smaller estimation error in the off-policy, offline setting.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":18,"citations":{"cited_by_in_corpus":2,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"unclassified":0},"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":2,"extracted_at":"2026-11-14T19:57:59Z"},"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/"}