{"paper_id":"2309.01784","title":"INTAGS: Interactive Agent-Guided Simulation","authors":["Song Wei","Andrea Coletta","Svitlana Vyetrenko","Tucker Balch"],"paper_date":"2023-09-04","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2309.01784v3","page_url":"https://thequant.space/flowcharts/intags-interactive-agent-guided-simulation/","scores":{"empirical_rigor":7,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the Interactive Agent-Guided Simulation (INTAGS) framework for building realistic agent-based simulators by optimizing a novel multi-agent system distance metric, and its market application called Algorithmic Trading‑guided Market Simulator (ATMS).","quote":"Importantly, we propose the Interactive Agent-Guided Simulation (INTAGS) framework to build a realistic ABS by optimizing over this novel metric. Based on this novel metric, we develop an online training framework, named Interactive Agent-Guided Simulation (INTAGS).","summary":"In many applications involving multi-agent system (MAS), it is imperative to test an experimental (Exp) autonomous agent in a high-fidelity simulator prior to its deployment to production, to avoid unexpected losses in the real-world. Such a simulator acts as the environmental background (BG)…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The simulator can be represented as a stochastic policy optimized via policy gradient without differentiating the metric.","type":"model","stated":"explicit","quote":"To adapt to any environment with interactive sequential decision making agents, INTAGS formulates the simulator as a stochastic policy in reinforcement learning. Moreover, INTAGS utilizes the policy gradient update to bypass differentiating the proposed metric such that it can support non-differentiable operations of multi-agent environments.","support":"full"},{"assumption":"The real environment is approximated by the ABIDES parametric simulator, treated as ground truth.","type":"market","stated":"explicit","quote":"Since we do not have access to real trading data, we consider a state-of-art parametric simulator as the real Env, where it is easier to obtain the “ground truth”; In particular, we take ABIDES [Byrd et al., 2020] with explicitly specified/parametric BG agents as “reality”.","support":"full"},{"assumption":"The experimental agent interacts with the environment only through offline replay data, which does not interfere with production.","type":"data","stated":"explicit","quote":"INTAGS only requires offline inter-actions/replays of the real-world experimental agent with the real environment, and thus will not interfere with the real-world production system; The framework is online because the objective function, or rather the proposed distance metric, is obtained through the online/live interaction of the real-world experimental agent with the synthetic environment.","support":"full"},{"assumption":"The optimal execution task assumes a fixed share size and time horizon for the AT agent.","type":"execution","stated":"explicit","quote":"The Exp agent is chosen as the AT agent that performs the optimal execution task, aiming to acquire a fixed share of a single asset within a fixed time horizon while minimizing the transaction cost.","support":"full"},{"assumption":"Feedback function f can be estimated from a small number of rollouts (e.g., Mkt2NextReturn).","type":"statistical","stated":"explicit","quote":"Thus, we choose Mkt2NextReturn as f that can differentiate markets with a small number of rollouts.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"ABIDES simulated market data","provider":null,"kind":"synthetic","access":"public","period":null,"universe":null,"quote":"Since we do not have access to real trading data, we consider a state-of-art parametric simulator as the real Env, where it is easier to obtain the “ground truth”; In particular, we take ABIDES [Byrd et al., 2020] with explicitly specified/parametric BG agents as “reality”. Using ABIDES data we train our simulated world BG agent.","support":"full","known_id":"abides"},{"name":"Rollout data T collected from experimental agent interactions","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"We use an ordered list T to denote the collection of states and actions when the Exp agent π interacts with the Env, and we name the collected data during (or after) this 6 interaction as rollout.","support":"full"}],"known":[{"id":"abides","name":"ABIDES simulator","provider":"ABIDES","kind":"synthetic","access":"public","quote":"Using ABIDES data we train our simulated world BG agent.","mentions":3,"used_in":1}],"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":"R4a","candidates":{"front_matter":"n/a","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"The AT agent’s objective is to minimize transaction cost while acquiring a fixed share amount within a time horizon.","card_quote":"The Exp agent is chosen as the AT agent that performs the optimal execution task, aiming to acquire a fixed share of a single asset within a fixed time horizon while minimizing the transaction cost.","meaning":"the paper reports no trading or execution result; the cost the extractor found is a model parameter"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"INTAGS calibrated simulators generate market data that is more realistic than the state‑of‑the‑art conditional Wasserstein GAN approach.","kind":"performance","quote":"We show that using INTAGS to calibrate the simulator can generate more realistic market data compared to the state-of-the-art conditional Wasserstein Generative Adversarial Network approach.","support":"full"},{"finding":"ATMS training reduces the AT‑based metric from 0.7156 to 0.6176, indicating improved similarity to reality.","kind":"performance","quote":"The corresponding AT-based metric is optimized from 0.7156 to 0.6176.","support":"full"},{"finding":"During ATMS training, volume at the first 10 LOB levels becomes increasingly similar to the real environment while the AT‑based metric is minimized.","kind":"performance","quote":"We can observe that, during the ATMS training, volume at first 10-levels is “increasingly similar” (in terms of magnitude and matching demand-supply) to reality while our AT-based metric is minimized. The ATMS can generate market data that is “increasingly” similar to reality while minimizing our AT-based metric.","support":"full"},{"finding":"ATMS outperforms the cWGAN baseline in matching stylized facts such as volume distribution and buy/sell balance.","kind":"performance","quote":"Next, we show that our ATMS outperforms existing cWGAN baseline [Coletta et al., 2022]; See Appendix C.3 for further details. Interestingly, we find that the stylized facts are not only similar to the target market but also show more balanced BUY and SELL volumes.","support":"full"},{"finding":"INTAGS training can be completed in about 2 hours on AWS r6i.24xlarge (96 CPUs, 768 GiB) by tuning hyperparameters.","kind":"other","quote":"This is because T0 (and b) determines how many BG agent actions are sampled and penalized, and thus can be treated as batch-size in stochastic GD; This makes T0 a tunable hyperparame-ter; By carefully tuning T0 (and b; see the hyperparameter selection in Appendix D.1), we can finish the INTAGS training within a reasonable time frame (around 2 hours) using Amazon Web Services (r6i.24xlarge, 96 CPUs, 768 GiB memory).","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":29,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"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":"2026-11-14T20:01:29Z"},"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/"}