5 citations · 17 across the 26 of their papers we have counts for
6 papers · 1 filter
Human-Like Goalkeeping in a Realistic Football Simulation: a Sample-Efficient Reinforcement Learning Approach
Alessandro Sestini, Joakim Bergdahl, Jean-Philippe Barrette-LaPierre +5
While several high profile video games have served as testbeds for Deep Reinforcement Learning (DRL), this technique has rarely been employed by the game industry for crafting auth…
Self-correcting Reward Shaping via Language Models for Reinforcement Learning Agents in Games
António Afonso, Iolanda Leite, Alessandro Sestini +3
Reinforcement Learning (RL) in games has gained significant momentum in recent years, enabling the creation of different agent behaviors that can transform a player's gaming experi…
TROFI: Trajectory-Ranked Offline Inverse Reinforcement Learning
Alessandro Sestini, Joakim Bergdahl, Konrad Tollmar +2
In offline reinforcement learning, agents are trained using only a fixed set of stored transitions derived from a source policy. However, this requires that the dataset be labeled…
Real-Time Diffusion Policies for Games: Enhancing Consistency Policies with Q-Ensembles
Ruoqi Zhang, Ziwei Luo, Jens Sjölund +3
Diffusion models have shown impressive performance in capturing complex and multi-modal action distributions for game agents, but their slow inference speed prevents practical depl…
Improving Sample Efficiency in Multi-Agent Reinforcement Learning for Simulated Football Games via Exploration
Amir Baghi, Jens Sjölund, Joakim Bergdahl +2
Multi-agent reinforcement learning has shown promise in learning cooperative behaviors in team-based environments. However, such methods often demand extensive training time, which…
SPEQ: Offline Stabilization Phases for Efficient Q-Learning in High Update-To-Data Ratio Reinforcement Learning
Carlo Romeo, Girolamo Macaluso, Alessandro Sestini +1
High update-to-data (UTD) ratio algorithms in reinforcement learning (RL) improve sample efficiency but incur high computational costs, limiting real-world scalability. We propose…