Toggle Poster Visibility
Spotlight
Wed Dec 05 12:30 PM -- 12:35 PM (PST) @ Room 220 CD
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation
Spotlight
Wed Dec 05 12:35 PM -- 12:40 PM (PST) @ Room 220 CD
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
Spotlight
Wed Dec 05 12:40 PM -- 12:45 PM (PST) @ Room 220 CD
Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
Spotlight
Wed Dec 05 12:45 PM -- 12:50 PM (PST) @ Room 220 CD
Meta-Reinforcement Learning of Structured Exploration Strategies
Oral
Wed Dec 05 12:50 PM -- 01:05 PM (PST) @ Room 220 CD
Policy Optimization via Importance Sampling
[
Video]
Spotlight
Wed Dec 05 01:05 PM -- 01:10 PM (PST) @ Room 220 CD
A Bayesian Approach to Generative Adversarial Imitation Learning
Spotlight
Wed Dec 05 01:10 PM -- 01:15 PM (PST) @ Room 220 CD
Visual Reinforcement Learning with Imagined Goals
Spotlight
Wed Dec 05 01:15 PM -- 01:20 PM (PST) @ Room 220 CD
Randomized Prior Functions for Deep Reinforcement Learning
Spotlight
Wed Dec 05 01:20 PM -- 01:25 PM (PST) @ Room 220 CD
Playing hard exploration games by watching YouTube
Oral
Wed Dec 05 01:25 PM -- 01:40 PM (PST) @ Room 220 CD
Recurrent World Models Facilitate Policy Evolution
[
Video]
Spotlight
Wed Dec 05 01:40 PM -- 01:45 PM (PST) @ Room 220 CD
Reducing Network Agnostophobia
[
Slides]
[
Indexed Video]
Spotlight
Wed Dec 05 01:45 PM -- 01:50 PM (PST) @ Room 220 CD
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies
[
Slides]
[
Indexed Video]
Spotlight
Wed Dec 05 01:50 PM -- 01:55 PM (PST) @ Room 220 CD
Geometrically Coupled Monte Carlo Sampling
Spotlight
Wed Dec 05 01:55 PM -- 02:00 PM (PST) @ Room 220 CD
Scalable Laplacian K-modes