← Authors

Misha Denil

20 papers · 2013–2024 · 7 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) 🐝 Cross-Pollinator (14) 🌈 Renaissance Researcher (7) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (11) πŸ—ΊοΈ Taxonomy Completionist (11) 🧭 Keyword Pioneer 🀝 Dynamic Duo (13) 🌱 Topic Pioneer πŸ’Ž Century Club (20) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (9) πŸš€ Conference Pioneer πŸ—ƒοΈ Keyword Collector (77)

Conferences

ICML (6) ICLR (4) NIPS (4) CORL (3) ICCV (1) INTERSPEECH (1) RSS (1)

Top co-authors

Nando de Freitas (13) Sergio GΓ³mez Colmenarejo (6) Ziyu Wang (5) Nando Freitas (4) Serkan Cabi (4) Caglar Gulcehre (4) Matthew W. Hoffman (4) Yutian Chen (3) Thomas Paine (3) Alexander Novikov (2)

Keywords

gradient descent (3) model compression (2) graphical model (2) reward learning (2) neural network optimization (2) reinforcement learning (2) bayesian optimization (2) markov random field (2) random forest (2) offline reinforcement learning (1) policy gradient (1) black-box optimization (1) parameter estimation (1) network pruning (1) reward modeling (1) robotic manipulation (1) continuous control (1) policy optimization (1) off-policy evaluation (1) simulated annealing (1)

Papers

$\pi$2vec: Policy Representation with Successor Features ICLR 2024
Active Offline Policy Selection NIPS 2021
Scaling data-driven robotics with reward sketching and batch reinforcement learning RSS 2020
Positive-Unlabeled Reward Learning CORL 2020
Task-Relevant Adversarial Imitation Learning CORL 2020
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems ICLR 2020
Hyperbolic Attention Networks ICLR 2019
Large-Scale Visual Speech Recognition INTERSPEECH 2019
Learning Awareness Models ICLR 2018
Learned Optimizers that Scale and Generalize ICML 2017
Learning to Learn without Gradient Descent by Gradient Descent ICML 2017
The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously CORL 2017
Noisy Activation Functions ICML 2016
Learning to learn by gradient descent by gradient descent NIPS 2016
Deep Fried Convnets ICCV 2015
Distributed Parameter Estimation in Probabilistic Graphical Models NIPS 2014
Narrowing the Gap: Random Forests In Theory and In Practice ICML 2014
Linear and Parallel Learning of Markov Random Fields ICML 2014
Predicting Parameters in Deep Learning NIPS 2013
Consistency of Online Random Forests ICML 2013