Picture for Dhruv Malik

Dhruv Malik

Beyond Parameter Count: Implicit Bias in Soft Mixture of Experts

Add code
Sep 02, 2024
Viaarxiv icon

Specifying and Solving Robust Empirical Risk Minimization Problems Using CVXPY

Add code
Jun 14, 2023
Viaarxiv icon

Weighted Tallying Bandits: Overcoming Intractability via Repeated Exposure Optimality

Add code
May 04, 2023
Viaarxiv icon

How Does Adaptive Optimization Impact Local Neural Network Geometry?

Add code
Nov 04, 2022
Viaarxiv icon

Complete Policy Regret Bounds for Tallying Bandits

Add code
Apr 24, 2022
Viaarxiv icon

Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity

Add code
Jun 15, 2021
Figure 1 for Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Figure 2 for Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Figure 3 for Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Figure 4 for Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity
Viaarxiv icon

When Is Generalizable Reinforcement Learning Tractable?

Add code
Jan 01, 2021
Figure 1 for When Is Generalizable Reinforcement Learning Tractable?
Figure 2 for When Is Generalizable Reinforcement Learning Tractable?
Figure 3 for When Is Generalizable Reinforcement Learning Tractable?
Figure 4 for When Is Generalizable Reinforcement Learning Tractable?
Viaarxiv icon

Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems

Add code
Dec 20, 2018
Figure 1 for Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
Viaarxiv icon

An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning

Add code
Jun 11, 2018
Figure 1 for An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
Figure 2 for An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
Figure 3 for An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
Figure 4 for An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
Viaarxiv icon

Pragmatic-Pedagogic Value Alignment

Add code
Feb 05, 2018
Figure 1 for Pragmatic-Pedagogic Value Alignment
Figure 2 for Pragmatic-Pedagogic Value Alignment
Viaarxiv icon