Learning to Represent Action Values as a Hypergraph on the Action Vertices
3. května 2021
Řečníci
Arash Tavakoli
Řečník · 0 sledujících
Mehdi Fatemi
Řečník · 0 sledujících
Petar Kormushev
Řečník · 0 sledujících
O prezentaci
Action-value estimation is a critical component of many reinforcement learning (RL) methods whereby sample complexity relies heavily on how fast a good estimator for action value can be learned. By viewing this problem through the lens of representation learning, good representations of both state and action can facilitate action-value estimation. While advances in deep learning have seamlessly driven progress in learning state representations, given the specificity of the notion of agency to RL, little attention has been paid to learning action representations. We conjecture that leveraging the combinatorial structure of multi-dimensional action spaces is a key ingredient for learning good representations of action. To test this, we set forth the action hypergraph networks framework---a class of functions for learning action representations in multi-dimensional discrete action spaces with a structural inductive bias. Using this framework we realise an agent class based on a combination with deep Q-networks, which we dub hypergraph Q-networks. We show the effectiveness of our approach on a myriad of domains: illustrative prediction problems under minimal confounding effects, Atari 2600 games, and discretised physical control benchmarks.Action-value estimation is a critical component of many reinforcement learning (RL) methods whereby sample complexity relies heavily on how fast a good estimator for action value can be learned. By viewing this problem through the lens of representation learning, good representations of both state and action can facilitate action-value estimation. While advances in deep learning have seamlessly driven progress in learning state representations, given the specificity of the notion of agency to RL…
Kategorie
Umělá inteligence a data science
Kategorie · 10,8k prezentací
O organizátorovi (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.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Aligning Text and Embodied Environments for Interactive Learning
Zhlédnout později
Sequential Density Ratio Estimation for Simultaneous Optimization of Speed and Accuracy
Zhlédnout později
Mapping the Timescale Organization of Neural Language Models
Zhlédnout později
S2D-OLAD: From shallow to deep, overcoming limited and adverse data
Zhlédnout později
Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies
Zhlédnout později
Paul Liang, …
