36 citations · 38 across the 7 of their papers we have counts for
7 papers
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…
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…
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…
Posterior Sampling for Deep Reinforcement Learning
Remo Sasso, Michelangelo Conserva, Paulo Rauber
Despite remarkable successes, deep reinforcement learning algorithms remain sample inefficient: they require an enormous amount of trial and error to find good policies. Model-base…
Hardness in Markov Decision Processes: Theory and Practice
Michelangelo Conserva, Paulo Rauber
Meticulously analysing the empirical strengths and weaknesses of reinforcement learning methods in hard (challenging) environments is essential to inspire innovations and assess pr…
Recurrent Neural-Linear Posterior Sampling for Nonstationary Contextual Bandits
Aditya Ramesh, Paulo Rauber, Michelangelo Conserva +1
An agent in a nonstationary contextual bandit problem should balance between exploration and the exploitation of (periodic or structured) patterns present in its previous experienc…
Hindsight policy gradients
Paulo Rauber, Avinash Ummadisingu, Filipe Mutz +1
A reinforcement learning agent that needs to pursue different goals across episodes requires a goal-conditional policy. In addition to their potential to generalize desirable behav…