What is the Value of an Action in Ice Hockey? Q-Learning for the NHL
نویسندگان
چکیده
Abstract. Recent work has applied the Markov Game formalism from AI to model game dynamics for ice hockey, using a large state space. Dynamic programming is used to learn action-value functions that quantify the impact of actions on goal scoring. Learning is based on a massive dataset that contains over 2.8M events in the National Hockey League. As an application of the Markov model, we use the learned action values to measure the impact of player actions on goal scoring. Players are ranked according to the aggregate goal impact of their actions. We show that this ranking is consistent across across seasons, and compare it with previous player metrics, such as plus-minus and total points.
منابع مشابه
What is the Value of an Action in Ice Hockey? Learning a Q-function for the NHL
Recent work has applied the Markov Game formalism from AI to model game dynamics for ice hockey, using a large state space. Dynamic programming is used to learn action-value functions that quantify the impact of actions on goal scoring. Learning is based on a massive dataset that contains over 2.8M events in the National Hockey League. As an application of the Markov model, we use the learned a...
متن کاملConcussions in the NHL: A narrative review of the literature.
Ice hockey has been identified as a sport with a high risk for concussions. Given the health sequelae associated with the injury, a great deal of attention has been placed on its diagnosis, management and return-to-play protocols. The highest level of ice hockey in North America is played in the National Hockey League (NHL), and concussions pose a serious threat to the health of the players and...
متن کاملOn-Line Learning of a Persian Spoken Dialogue System Using Real Training Data
The first spoken dialogue system developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (g) on the learning speed...
متن کاملOn-Line Learning of a Persian Spoken Dialogue System Using Real Training Data
The first spoken dialogue system developed for the Persian language is introduced. This is a ticket reservation system with Persian ASR and NLU modules. The focus of the paper is on learning the dialogue management module. In this work, real on-line training data are used during the learning process. For on-line learning, the effect of the variations of discount factor (g) on the learning speed...
متن کاملReinforcement learning based feedback control of tumor growth by limiting maximum chemo-drug dose using fuzzy logic
In this paper, a model-free reinforcement learning-based controller is designed to extract a treatment protocol because the design of a model-based controller is complex due to the highly nonlinear dynamics of cancer. The Q-learning algorithm is used to develop an optimal controller for cancer chemotherapy drug dosing. In the Q-learning algorithm, each entry of the Q-table is updated using data...
متن کامل