3 papers
cs.LG2026
A KL-regularization Framework for Learning to Plan with Adaptive Priors
Ãlvaro Serra-Gomez, Daniel Jarne Ornia, Dhruva Tirumala +1
Effective exploration remains a central challenge in model-based reinforcement learning (MBRL), particularly in high-dimensional continuous control tasks where sample efficiency is…
cs.RO2025
Predictability Awareness for Efficient and Robust Multi-Agent Coordination
Roman Chiva Gil, Daniel Jarne Ornia, Khaled A. Mustafa +1
To safely and efficiently solve motion planning problems in multi-agent settings, most approaches attempt to solve a joint optimization that explicitly accounts for the responses t…
cs.LG2025
Predictable Reinforcement Learning Dynamics through Entropy Rate Minimization
Daniel Jarne Ornia, Giannis Delimpaltadakis, Jens Kober +1
In Reinforcement Learning (RL), agents have no incentive to exhibit predictable behaviors, and are often pushed (through e.g. policy entropy regularisation) to randomise their acti…