Light-weight probing of unsupervised representations for Reinforcement Learning

1 code implementation • 25 Aug 2022 • Wancong Zhang, Anthony GX-Chen, Vlad Sobal, Yann Lecun, Nicolas Carion

Unsupervised visual representation learning offers the opportunity to leverage large corpora of unlabeled trajectories to form useful visual representations, which can benefit the training of reinforcement learning (RL) algorithms.

reinforcement-learning Reinforcement Learning (RL) +2

A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions

no code implementations • 5 Jan 2022 • Anthony GX-Chen, Veronica Chelu, Blake A. Richards, Joelle Pineau

We illustrate that incorporating predictive knowledge through an $\eta\gamma$-discounted SF model makes more efficient use of sampled experience, compared to either extreme, i. e. bootstrapping entirely on the value function estimate, or bootstrapping on the product of separately estimated successor features and instantaneous reward models.