Imitation with Neural Density Models
6. prosince 2021
Řečníci
Akshat Jindal
Speaker · 0 followers
Jiaming Song
Speaker · 3 followers
Stefano Ermon
Speaker · 15 followers
O prezentaci
We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward. Our approach maximizes a non-adversarial model-free RL objective that provably lower bounds reverse Kullback–Leibler divergence between occupancy measures of the expert and imitator. We present a practical IL algorithm, Neural Density Imitation (NDI), which obtains state-of-the-art demonstration efficiency on benchmark control tasks.We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward. Our approach maximizes a non-adversarial model-free RL objective that provably lower bounds reverse Kullback–Leibler divergence between occupancy measures of the expert and imitator. We present a practical IL algorithm, Neural Density Imitation (NDI), which obtains state-of-the-art demonstr…
Organizátor
NeurIPS 2021
Account · 1.9k followers
O organizátorovi (NeurIPS 2021)
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
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
NATURE: Natural Auxiliary Text Utterances for Realistic Spoken Language Evaluation
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Exploring the Limits of Out-of-Distribution Detection
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios
Watch later
Total of 1 viewers voted for saving the presentation to eternal vault which is 0.1%
Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems
Watch later
Jiayang Xu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%