Toggle Poster Visibility
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #1
Soft Q-Learning with Mutual-Information Regularization
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #2
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #3
Visceral Machines: Risk-Aversion in Reinforcement Learning with Intrinsic Physiological Rewards
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #4
Knowledge Flow: Improve Upon Your Teachers
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #5
Meta-learning with differentiable closed-form solvers
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #6
Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #7
Probabilistic Planning with Sequential Monte Carlo methods
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #8
Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #9
Combinatorial Attacks on Binarized Neural Networks
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #11
Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #12
Two-Timescale Networks for Nonlinear Value Function Approximation
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #13
KnockoffGAN: Generating Knockoffs for Feature Selection using Generative Adversarial Networks
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #14
Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #15
Competitive experience replay
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #17
Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #18
Neural Program Repair by Jointly Learning to Localize and Repair
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #19
FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #20
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #21
M^3RL: Mind-aware Multi-agent Management Reinforcement Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #22
Learning Actionable Representations with Goal Conditioned Policies
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #23
Neural Graph Evolution: Automatic Robot Design
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #24
Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guarantees
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #25
Episodic Curiosity through Reachability
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #26
A new dog learns old tricks: RL finds classic optimization algorithms
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #27
Optimal Completion Distillation for Sequence Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #28
Hierarchical Visuomotor Control of Humanoids
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #29
Meta-Learning For Stochastic Gradient MCMC
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #30
Environment Probing Interaction Policies
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #31
Relational Forward Models for Multi-Agent Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #32
Deterministic Variational Inference for Robust Bayesian Neural Networks
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #33
Emergent Coordination Through Competition
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #34
Variance Reduction for Reinforcement Learning in Input-Driven Environments
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #35
A comprehensive, application-oriented study of catastrophic forgetting in DNNs
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #36
Information asymmetry in KL-regularized RL
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #37
Modeling the Long Term Future in Model-Based Reinforcement Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #38
Synthetic Datasets for Neural Program Synthesis
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #39
Unsupervised Learning via Meta-Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #40
Learning to Navigate the Web
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #41
Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #42
Sample Efficient Adaptive Text-to-Speech
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #43
CEM-RL: Combining evolutionary and gradient-based methods for policy search
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #44
An Empirical Study of Example Forgetting during Deep Neural Network Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #45
Learning Multi-Level Hierarchies with Hindsight
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #46
Reward Constrained Policy Optimization
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #47
Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #48
Supervised Policy Update for Deep Reinforcement Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #49
Towards Metamerism via Foveated Style Transfer
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #50
Deep Online Learning Via Meta-Learning: Continual Adaptation for Model-Based RL
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #51
Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #52
Analysing Mathematical Reasoning Abilities of Neural Models
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #53
Execution-Guided Neural Program Synthesis
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #54
Learning deep representations by mutual information estimation and maximization
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #55
Meta-Learning Probabilistic Inference for Prediction
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #56
Solving the Rubik's Cube with Approximate Policy Iteration
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #57
Universal Successor Features Approximators
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #58
Information-Directed Exploration for Deep Reinforcement Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #59
Learning Exploration Policies for Navigation
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #61
ProMP: Proximal Meta-Policy Search
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #62
AutoLoss: Learning Discrete Schedule for Alternate Optimization
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #63
Neural Probabilistic Motor Primitives for Humanoid Control
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #65
Adaptive Posterior Learning: few-shot learning with a surprise-based memory module
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #67
The Laplacian in RL: Learning Representations with Efficient Approximations
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #68
Exploration by random network distillation
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #69
Composing Complex Skills by Learning Transition Policies
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #70
Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #71
Measuring and regularizing networks in function space
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #72
Learning to Schedule Communication in Multi-agent Reinforcement Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #73
LEARNING TO PROPAGATE LABELS: TRANSDUCTIVE PROPAGATION NETWORK FOR FEW-SHOT LEARNING
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #74
NADPEx: An on-policy temporally consistent exploration method for deep reinforcement learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #75
Policy Transfer with Strategy Optimization
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #76
Large-Scale Study of Curiosity-Driven Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #77
Diversity is All You Need: Learning Skills without a Reward Function
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #78
Preferences Implicit in the State of the World
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #79
Learning to Learn with Conditional Class Dependencies
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #80
Hierarchical Reinforcement Learning via Advantage-Weighted Information Maximization
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #81
Efficient Lifelong Learning with A-GEM
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #82
Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #83
Automatically Composing Representation Transformations as a Means for Generalization
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #84
Contingency-Aware Exploration in Reinforcement Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #85
Overcoming Catastrophic Forgetting for Continual Learning via Model Adaptation
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #86
A Closer Look at Few-shot Classification
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #87
On Random Deep Weight-Tied Autoencoders: Exact Asymptotic Analysis, Phase Transitions, and Implications to Training
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #88
Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #89
Opportunistic Learning: Budgeted Cost-Sensitive Learning from Data Streams
[
PDF]
Poster
Wed May 08 09:00 AM -- 11:00 AM (PDT) @ Great Hall BC #90
Selfless Sequential Learning
[
PDF]