DRL-driven padel players: Simulating padel matches through deep reinforcement learning in real and hypothetical scenarios
Recent advances in Deep Reinforcement Learning (DRL) have opened new avenues for sport research. DRL allows virtual agents to learn and solve complex tasks with minimal input, which means that models can be trained with little or no data collection. This enables the creation of sport simulations tha...
| Authors: | , , , , |
|---|---|
| Format: | article |
| Publication Date: | 2025 |
| Country: | España |
| Institution: | Universitat Politècnica de Catalunya (UPC) |
| Repository: | UPCommons. Portal del coneixement obert de la UPC |
| Language: | English |
| OAI Identifier: | oai:upcommons.upc.edu:2117/439547 |
| Online Access: | https://hdl.handle.net/2117/439547 https://dx.doi.org/10.1080/02640414.2025.2518693 |
| Access Level: | Open access |
| Keyword: | Racket sports Artificial inteligence Imitation learning Virtual agents Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic Àrees temàtiques de la UPC::Informàtica::Aplicacions de la informàtica |
| Summary: | Recent advances in Deep Reinforcement Learning (DRL) have opened new avenues for sport research. DRL allows virtual agents to learn and solve complex tasks with minimal input, which means that models can be trained with little or no data collection. This enables the creation of sport simulations that go beyond the replication of real matches, exploring entirely new conditions where prior knowledge is limited. In this paper, we investigate the generation of simulated data for padel matches, aiming to either replicate real environments or investigate hypothetical ones with altered parameters such as non-standard court sizes. We focus on high-level behavioural aspects of the players rather than low-level skills. We present a proof-of-concept implementation of a DRL system that enables robot-like agents to learn and play padel under varying conditions. After training different types of virtual agents, we observed their overall behaviour during simulated matches. In particular, for certain combinations of parameters, the agents learned to coordinate their movements similarly to professional players. We argue that DRL-driven players have the potential to complement traditional mathematical models, especially in scenarios where data collection is challenging or unfeasible. This could lead to more engaging, safer and more inclusive sports in the future. |
|---|