{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/financial-trading-as-a-game-a-deep","title":"Financial Trading as a Game: A Deep Reinforcement Learning Approach","arxiv_id":"1807.02787","date":"2018-07-08","proceeding":null,"authors":["Chien Yi Huang"],"abstract":"An automatic program that generates constant profit from the financial market\nis lucrative for every market practitioner. Recent advance in deep\nreinforcement learning provides a framework toward end-to-end training of such\ntrading agent. In this paper, we propose an Markov Decision Process (MDP) model\nsuitable for the financial trading task and solve it with the state-of-the-art\ndeep recurrent Q-network (DRQN) algorithm. We propose several modifications to\nthe existing learning algorithm to make it more suitable under the financial\ntrading setting, namely 1. We employ a substantially small replay memory (only\na few hundreds in size) compared to ones used in modern deep reinforcement\nlearning algorithms (often millions in size.) 2. We develop an action\naugmentation technique to mitigate the need for random exploration by providing\nextra feedback signals for all actions to the agent. This enables us to use\ngreedy policy over the course of learning and shows strong empirical\nperformance compared to more commonly used epsilon-greedy exploration. However,\nthis technique is specific to financial trading under a few market assumptions.\n3. We sample a longer sequence for recurrent neural network training. A side\nproduct of this mechanism is that we can now train the agent for every T steps.\nThis greatly reduces training time since the overall computation is down by a\nfactor of T. We combine all of the above into a complete online learning\nalgorithm and validate our approach on the spot foreign exchange market.","url_abs":"http://arxiv.org/abs/1807.02787v1","url_pdf":"http://arxiv.org/pdf/1807.02787v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"financial-trading-as-a-game-a-deep","repo_url":"https://github.com/sachink2010/AutomatedStockTrading-DeepQ-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1807.02787","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}