5 papers
Robust Successor Features
Erik Nikulski, Yamen Habib, Vicenç Gomez +3
Generalization in Reinforcement Learning (RL) refers to the ability to execute close-to-optimal policies in unseen tasks after the agent has been trained on a different set of task…
From Next Token Prediction to (STRIPS) World Models
Carlos Núñez-Molina, Vicenç Gómez, Hector Geffner
We study whether next-token prediction can yield world models that truly support planning, in a controlled symbolic setting where propositional STRIPS action models are learned fro…
Hierarchical Average-Reward Linearly-solvable Markov Decision Processes
Guillermo Infante, Anders Jonsson, Vicenç Gómez
We introduce a novel approach to hierarchical reinforcement learning for Linearly-solvable Markov Decision Processes (LMDPs) in the infinite-horizon average-reward setting. Unlike…
Planning with a Learned Policy Basis to Optimally Solve Complex Tasks
Guillermo Infante, David Kuric, Anders Jonsson +2
Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably acr…
Hierarchical Width-Based Planning and Learning
Miquel Junyent, Vicenç Gómez, Anders Jonsson
Width-based search methods have demonstrated state-of-the-art performance in a wide range of testbeds, from classical planning problems to image-based simulators such as Atari game…