2021-12
Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs
2021-11
Sometimes We Want Ungrammatical Translations
2021-10
Block Contextual MDPs for Continual Learning.
Circulating proteins to predict adverse COVID-19 outcomes
2021-08
UnNatural Language Inference
Improving reproducibility in machine learning research : a report from the NeurIPS 2019 reproducibility program
Journal of Machine Learning Research
(2021-08-01)
hal.archives-ouvertes.frPDF[Also on arXiv preprint arXiv:2003.12206 (2020-03-27)]2021-07
A BRIEF STUDY ON THE EFFECTS OF TRAINING GENERATIVE DIALOGUE MODELS WITH A SEMANTIC LOSS
DO ENCODER REPRESENTATIONS OF GENERATIVE DIALOGUE MODELS HAVE SUFFICIENT SUMMARY OF THE INFORMATION ABOUT THE TASK
Automated Data-Driven Generation of Personalized Pedagogical Interventions in Intelligent Tutoring Systems
OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation
Multi-Task Reinforcement Learning with Context-based Representations
2021-06
Do Encoder Representations of Generative Dialogue Models Encode Sufficient Information about the Task
A Brief Study on the Effects of Training Generative Dialogue Models with a Semantic loss
SPeCiaL: Self-Supervised Pretraining for Continual Learning.
2021-05
Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations
Correcting Momentum in Temporal Difference Learning
GraphLog: A Benchmark for Measuring Logical Generalization in Graph Neural Networks
Learning Robust State Abstractions for Hidden-Parameter Block MDPs
Regularized Inverse Reinforcement Learning
2021-04
Sometimes We Want Translationese.
Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little
Reducing Representation Drift in Online Continual Learning.
Exploring the Limits of Few-Shot Link Prediction in Knowledge Graphs.
2021-03
Quasi-Equivalence Discovery for Zero-Shot Emergent Communication.
Model-Invariant State Abstractions for Model-Based Reinforcement Learning
Resolving Causal Confusion in Reinforcement Learning via Robust Exploration
2021-02
Domain Adversarial Reinforcement Learning.
2021-01
COVID-19 Prognosis via Self-Supervised Representation Learning and Multi-Image Prediction
COVID-19 Deterioration Prediction via Self-Supervised Representation Learning and Multi-Image Prediction
Democratising the Digital Revolution: The Role of Data Governance
Reflections on Artificial Intelligence for Humanity
(2021-01-01)
doi.org[Also on Social Science Research Network (2020-06-30)]TDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning?
2020-12
Intervention Design for Effective Sim2Real Transfer.
2020-11
RapidBrachyDL: Rapid Radiation Dose Calculations in Brachytherapy Via Deep Learning.
2020-10
The Bottleneck Simulator: A Model-Based Deep Reinforcement Learning Approach
Journal of Artificial Intelligence Research
(2020-10-27)
dblp.uni-trier.dePDF[Also on arXiv preprint arXiv:1807.04723 (2018-07-12)]Transparency and reproducibility in artificial intelligence.
2020-08
Stable Policy Optimization via Off-Policy Divergence Regularization.
How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
2020-07
Plan2Vec: Unsupervised Representation Learning by Latent Plans
Learning for Dynamics and Control
(2020-07-31)
proceedings.mlr.pressPDF[Also on arXiv preprint arXiv:2005.03648 (2020-05-07)]Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP
Building reproducible, reusable, and robust machine learning software
Constrained Markov Decision Processes via Backward Value Functions
Invariant Causal Prediction for Block MDPs
Online Learned Continual Compression with Adaptive Quantization Modules
Interference and Generalization in Temporal Difference Learning
Handling Black Swan Events in Deep Learning with Diversely Extrapolated Neural Networks
On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract).
Automated Personalized Feedback Improves Learning Gains in An Intelligent Tutoring System
TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM
Deep interpretability for GWAS.
Development of a polygenic risk score to improve screening for fracture risk: A genetic risk prediction study
Learning an Unreferenced Metric for Online Dialogue Evaluation.
2020-06
Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization
Evaluating Logical Generalization in Graph Neural Networks.
Machine Learning for COVID-19 needs global collaboration and data-sharing
2020-04
On the interaction between supervision and self-play in emergent communication
Language GANs Falling Short
Literature Mining for Incorporating Inductive Bias in Biomedical Prediction Tasks (Student Abstract)
Exploiting Spatial Invariance for Scalable Unsupervised Object Tracking
2020-03
Invariant Causal Prediction for Block MDPs.
2020-02
The importance of transparency and reproducibility in artificial intelligence research
Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic.
Representation of Reinforcement Learning Policies in Reproducing Kernel Hilbert Spaces.
Provably efficient reconstruction of policy networks.
2020-01
Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning
Journal of Machine Learning Research
(2020-01-31)
jmlr.csail.mit.eduPDF[LATEST on arXiv preprint arXiv:2002.05651 (2020-01-31)]Novelty Search in Representational Space for Sample Efficient Exploration
Machine learning to predict osteoporotic fracture risk from genotypes
2019-12
Off-Policy Policy Gradient Algorithms by Constraining the State Distribution Shift. (arXiv:1911.06970v2 [cs.LG] UPDATED)
arXiv Computer Science
(2019-12-03)
2019-11
Online Learned Continual Compression with Stacked Quantization Module.
Seeded self-play for language learning
CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text
Deep Generative Modeling of LiDAR Data
2019-10
MVFST-RL: An Asynchronous RL Framework for Congestion Control with Delayed Actions.
Recurrent Value Functions. (arXiv:1905.09562v1 [cs.LG])
arXiv Computer Science
(2019-10-07)
Benchmarking Batch Deep Reinforcement Learning Algorithms.
2019-09
Assessing Generalization in TD methods for Deep Reinforcement Learning
Attraction-Repulsion Actor-Critic for Continuous Control Reinforcement Learning
Improving Sample Efficiency in Model-Free Reinforcement Learning from Images
No Press Diplomacy: Modeling Multi-Agent Gameplay
No-Press Diplomacy: Modeling Multi-Agent Gameplay
2019-07
Spatially Invariant Unsupervised Object Detection with Convolutional Neural Networks
On-line Adaptative Curriculum Learning for GANs
Combined Reinforcement Learning via Abstract Representations
2019-06
Learning Causal State Representations of Partially Observable Environments
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
2019-05
Separating value functions across time-scales
TarMAC: Targeted Multi-Agent Communication
Recurrent Value Functions.
ICLR Reproducibility Challenge 2019
Leveraging exploration in off-policy algorithms via normalizing flows
On the Pitfalls of Measuring Emergent Communication
Task-Agnostic Reinforcement Learning (TARL)
On overfitting and asymptotic bias in batch reinforcement learning with partial observability
2019-04
Multitask Metric Learning: Theory and Algorithm
2019-03
An Introduction to Deep Reinforcement Learning
(venue unknown)
(2019-03-31)
nowpublishers.comPDF[Also on arXiv preprint arXiv:1811.12560 (2018-11-30)]2019-01
The Second Conversational Intelligence Challenge (ConvAI2)
Leveraging exploration in off-policy algorithms via normalizing flows.
When AIs Outperform Doctors: Confronting the Challenges of a Tort-Induced Over-Reliance on Machine Learning
Ariz. L. Rev.
(2019-01-01)
repository.law.miami.eduPDF[LATEST on Social Science Research Network (2019-02-20)]2018-12
Ethical Challenges in Data-Driven Dialogue Systems
An Introduction to Deep Reinforcement Learning
2018-11
Contextual Bandits for Adapting Treatment in a Mouse Model of de Novo Carcinogenesis
Natural Environment Benchmarks for Reinforcement Learning
Compositional Language Understanding with Text-based Relational Reasoning.
The RLLChatbot: a solution to the ConvAI challenge.
Temporal Regularization in Markov Decision Process
2018-10
Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods.
2018-07
Focused Hierarchical RNNs for Conditional Sequence Processing
2018-06
A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning
RE-EVALUATE: Reproducibility in Evaluating Reinforcement Learning Algorithms
Randomized Value Functions via Multiplicative Normalizing Flows
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version
2018-02
Disentangling the independently controllable factors of variation by interacting with the world
Sequential Coordination of Deep Models for Learning Visual Arithmetic
An inference-based policy gradient method for learning options
Reward Estimation for Variance Reduction in Deep Reinforcement Learning
Conference on Robot Learning
(2018-02-12)
proceedings.mlr.pressPDF[LATEST on arXiv preprint arXiv:1805.03359 (2018-05-09)]Decoupling Dynamics and Reward for Transfer Learning.
OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning
Deep Reinforcement Learning that Matters
2018-01
A Deep Reinforcement Learning Chatbot (Short Version)
Genomic Prediction of Osteoporosis Using 426,000 Individuals from UK Biobank
Temporal Regularization for Markov Decision Process
A Decision-Theoretic Approach for the Collaborative Control of a Smart Wheelchair
Streaming kernel regression with provably adaptive mean, variance, and regularization
Reward Estimation for Variance Reduction in Deep Reinforcement Learning.
Extending Neural Generative Conversational Model using External Knowledge Sources
Publications collected and formatted using Paperoni