25 citations · 38 across the 9 of their papers we have counts for
5 papers · 1 filter
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
Adam Block, Dylan J. Foster, Akshay Krishnamurthy +2
This work studies training instabilities of behavior cloning with deep neural networks. We observe that minibatch SGD updates to the policy network during training result in sharp…
Statistical Learning under Heterogeneous Distribution Shift
Max Simchowitz, Anurag Ajay, Pulkit Agrawal +1
This paper studies the prediction of a target from a pair of random variables , where the ground-truth predictor is additive $\mathbb{E}[\math…
Bayesian decision-making under misspecified priors with applications to meta-learning
Max Simchowitz, Christopher Tosh, Akshay Krishnamurthy +4
Thompson sampling and other Bayesian sequential decision-making algorithms are among the most popular approaches to tackle explore/exploit trade-offs in (contextual) bandits. The c…
Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz +5
We introduce a new problem setting for continuous control called the LQR with Rich Observations, or RichLQR. In our setting, the environment is summarized by a low-dimensional cont…
Reward-Free Exploration for Reinforcement Learning
Chi Jin, Akshay Krishnamurthy, Max Simchowitz +1
Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To iso…