1.8 KiB
1.8 KiB
title, source, authors, affiliation, year, category, published
| title | source | authors | affiliation | year | category | published |
|---|---|---|---|---|---|---|
| Representation Learning Enables Scalable Multitask Deep RL | arXiv:2606.05555v1 | Johan Obando-Ceron, Lu Li, Scott Fujimoto, Pierre-Luc Bacon, Aaron Courville, Pablo Samuel Castro | Mila, Universite de Montreal, McGill, Google DeepMind | 2026 | cs.LG, cs.AI | 2026-06-04 |
Representation Learning Enables Scalable Multitask Deep RL
Authors: Johan Obando-Ceron, Lu Li, Scott Fujimoto, Pierre-Luc Bacon, Aaron Courville, Pablo Samuel Castro arXiv: 2606.05555v1 [cs.LG, cs.AI] Affiliations: Mila / UdeM / McGill / CIFAR / Google DeepMind Published: 2026-06-04
Abstract
Scaling RL to diverse multitask settings is a central challenge. We argue the primary driver is not model-based control but representation learning. Combining predictive model-based representations with high-capacity value function approximation is sufficient — even without planning. MR.Q, a model-free algorithm with auxiliary predictive objectives, outperforms world-model-based methods (Newt) while reducing computational overhead and improving wall-clock efficiency.
Key Concepts
- predictive-representation-learning — core thesis
- mrq-algorithm — the model-free agent with predictive objectives
- multitask-rl — training across diverse task distributions
- representation-learning-rl — beyond reward-only supervision
- auxiliary-predictive-objectives — dynamics/reward/termination prediction
- world-models-rl — model-based comparison point
- model-free-rl — the advocated approach
- deep-rl-scaling — the broader goal