Akshay Krishnamurthy

papers

935

total citations

papers (16)

Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination

NEURIPS 2021arXiv

citations

Bayesian decision-making under misspecified priors with applications to meta-learning

NEURIPS 2021arXiv

citations

Efficient Contextual Bandits with Continuous Actions

NEURIPS 2020arXiv

citations

Learning the Linear Quadratic Regulator from Nonlinear Observations

NEURIPS 2020arXiv

citations

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL

NEURIPS 2022arXiv

citations

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

ICLR 2024arXiv

citations

Scalable Online Exploration via Coverability

ICML 2024arXiv

citations

Provably adaptive reinforcement learning in metric spaces

NEURIPS 2020arXiv

citations

Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics

ICLR 2025arXiv

citations

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

ICML 2024arXiv

citations

Akshay Krishnamurthy

papers (16)

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

Information Theoretic Regret Bounds for Online Nonlinear Control

Gone Fishing: Neural Active Learning with Fisher Embeddings

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

Exposing Attention Glitches with Flip-Flop Language Modeling

Self-Improvement in Language Models: The Sharpening Mechanism

Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination

Bayesian decision-making under misspecified priors with applications to meta-learning

Efficient Contextual Bandits with Continuous Actions

Learning the Linear Quadratic Regulator from Nonlinear Observations

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Scalable Online Exploration via Coverability

Provably adaptive reinforcement learning in metric spaces

Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

papers (16)

FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs

Information Theoretic Regret Bounds for Online Nonlinear Control

Gone Fishing: Neural Active Learning with Fisher Embeddings

Sample-Efficient Reinforcement Learning of Undercomplete POMDPs

Exposing Attention Glitches with Flip-Flop Language Modeling

Self-Improvement in Language Models: The Sharpening Mechanism

Efficient First-Order Contextual Bandits: Prediction, Allocation, and Triangular Discrimination

Bayesian decision-making under misspecified priors with applications to meta-learning

Efficient Contextual Bandits with Continuous Actions

Learning the Linear Quadratic Regulator from Nonlinear Observations

On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Scalable Online Exploration via Coverability

Provably adaptive reinforcement learning in metric spaces

Computationally Efficient RL under Linear Bellman Completeness for Deterministic Dynamics

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics