Picture for Ashutosh Nayyar

Ashutosh Nayyar

Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning

Add code
Aug 17, 2024
Figure 1 for Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning
Figure 2 for Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning
Figure 3 for Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning
Figure 4 for Markov Balance Satisfaction Improves Performance in Strictly Batch Offline Imitation Learning
Viaarxiv icon

Pure Exploration for Constrained Best Mixed Arm Identification with a Fixed Budget

Add code
May 23, 2024
Viaarxiv icon

Model approximation in MDPs with unbounded per-step cost

Add code
Feb 13, 2024
Figure 1 for Model approximation in MDPs with unbounded per-step cost
Figure 2 for Model approximation in MDPs with unbounded per-step cost
Figure 3 for Model approximation in MDPs with unbounded per-step cost
Figure 4 for Model approximation in MDPs with unbounded per-step cost
Viaarxiv icon

Regret Analysis of the Posterior Sampling-based Learning Algorithm for Episodic POMDPs

Add code
Oct 16, 2023
Viaarxiv icon

Conditional Kernel Imitation Learning for Continuous State Environments

Add code
Aug 24, 2023
Figure 1 for Conditional Kernel Imitation Learning for Continuous State Environments
Figure 2 for Conditional Kernel Imitation Learning for Continuous State Environments
Viaarxiv icon

Optimal Control of Logically Constrained Partially Observable and Multi-Agent Markov Decision Processes

Add code
May 24, 2023
Viaarxiv icon

A Novel Point-based Algorithm for Multi-agent Control Using the Common Information Approach

Add code
Apr 10, 2023
Viaarxiv icon

Learning Zero-sum Stochastic Games with Posterior Sampling

Add code
Sep 08, 2021
Viaarxiv icon

A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems

Add code
Aug 19, 2021
Figure 1 for A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
Figure 2 for A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
Figure 3 for A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems
Viaarxiv icon

Scalable regret for learning to control network-coupled subsystems with unknown dynamics

Add code
Aug 18, 2021
Figure 1 for Scalable regret for learning to control network-coupled subsystems with unknown dynamics
Figure 2 for Scalable regret for learning to control network-coupled subsystems with unknown dynamics
Figure 3 for Scalable regret for learning to control network-coupled subsystems with unknown dynamics
Viaarxiv icon