3 papers
cs.LG2025
Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches
Remo Sasso, Michelangelo Conserva, Dominik Jeurissen +1
Exploration in reinforcement learning (RL) remains challenging, particularly in sparse-reward settings. While foundation models possess strong semantic priors, their capabilities a…
cs.LG2025
On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark
Michelangelo Conserva, Remo Sasso, Paulo Rauber
Principled evaluation is critical for progress in deep reinforcement learning (RL), yet it lags behind the theory-driven benchmarks of tabular RL. While tabular settings benefit fr…
cs.LG2025
Foundation Models as World Models: A Foundational Study in Text-Based GridWorlds
Remo Sasso, Michelangelo Conserva, Dominik Jeurissen +1
While reinforcement learning from scratch has shown impressive results in solving sequential decision-making tasks with efficient simulators, real-world applications with expensive…