Return-Based Contrastive Representation Learning for Reinforcement Learning
Mai 3, 2021
Sprecher:innen
Guoqing Liu
Řečník · 0 sledujících
Chuheng Zhang
Řečník · 0 sledujících
Jinhua Zhu
Řečník · 0 sledujících
Nenghai Yu
Řečník · 0 sledujících
Tie-Yan Liu
Řečník · 1 sledující
Über
Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems into consideration and are unsupervised. By leveraging returns, the most important feedback signals in RL, we propose a novel auxiliary task that forces the learnt representations to discriminate state-action pairs with different returns. Our auxiliary loss is theoretically justified to learn representations that capture the structure of a new form of state-action abstraction, under which state-action pairs with similar return distributions are aggregated together. Empirically, our algorithm outperforms strong baselines on complex tasks in Atari games and DeepMind Control suite, and achieves even better performance when combined with existing auxiliary tasks.Recently, various auxiliary tasks have been proposed to accelerate representation learning and improve sample efficiency in deep reinforcement learning (RL). However, existing auxiliary tasks do not take the characteristics of RL problems into consideration and are unsupervised. By leveraging returns, the most important feedback signals in RL, we propose a novel auxiliary task that forces the learnt representations to discriminate state-action pairs with different returns. Our auxiliary loss is…
Über ICLR 2021
The International Conference on Learning Representations (ICLR) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence called representation learning, but generally referred to as deep learning. ICLR is globally renowned for presenting and publishing cutting-edge research on all aspects of deep learning used in the fields of artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, text understanding, gaming, and robotics.
Gefällt euch das Format? Vertraut auf SlidesLive, um euer nächstes Event festzuhalten!
Professionelle Aufzeichnung und Livestreaming – weltweit.
Freigeben
Empfohlene Videos
Präsentationen, deren Thema, Kategorie oder Sprecher:in ähnlich sind
Closing remarks
Zhlédnout později
Structure Leaning and the Hippocampal-Entorhinal Circuit
Zhlédnout později
Learning Task-General Representations with Generative Neuro-Symbolic Modeling
Zhlédnout později
DICE: Diversity In Deep Ensembles Via Conditional Redundancy Adversarial Estimation
Zhlédnout později
