2.6k citations · 8.6k across the 77 of their papers we have counts for
6 papers · 2 filters
Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy +1
We present an algorithm, HOMER, for exploration and reinforcement learning in rich observation environments that are summarizable by an unknown latent state space. The algorithm in…
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy +2
We design a new algorithm for batch active learning with deep neural network models. Our algorithm, Batch Active learning by Diverse Gradient Embeddings (BADGE), samples groups of…
Empirical Likelihood for Contextual Bandits
Nikos Karampatziakis, John Langford, Paul Mineiro
We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. To this end we apply empirical likelihood…
Efficient Forward Architecture Search
Hanzhang Hu, John Langford, Rich Caruana +3
We propose a neural architecture search (NAS) algorithm, Petridish, to iteratively add shortcut connections to existing network layers. The added shortcut connections effectively p…
Provably efficient RL with Rich Observations via Latent State Decoding
Simon S. Du, Akshay Krishnamurthy, Nan Jiang +3
We study the exploration problem in episodic MDPs with rich observations generated from a small number of latent states. Under certain identifiability assumptions, we demonstrate h…
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback
Chicheng Zhang, Alekh Agarwal, Hal Daumé +2
We investigate the feasibility of learning from a mix of both fully-labeled supervised data and contextual bandit data. We specifically consider settings in which the underlying le…