Picture for Pradeep Varakantham

Pradeep Varakantham

Optimizing Ride-Pooling Operations with Extended Pickup and Drop-Off Flexibility

Add code
Mar 11, 2025
Viaarxiv icon

Improving Environment Novelty Quantification for Effective Unsupervised Environment Design

Add code
Feb 08, 2025
Viaarxiv icon

On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression

Add code
Jan 16, 2025
Figure 1 for On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
Figure 2 for On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
Figure 3 for On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
Figure 4 for On Learning Informative Trajectory Embeddings for Imitation, Classification and Regression
Viaarxiv icon

Offline Safe Reinforcement Learning Using Trajectory Classification

Add code
Dec 19, 2024
Viaarxiv icon

IRL for Restless Multi-Armed Bandits with Applications in Maternal and Child Health

Add code
Dec 11, 2024
Viaarxiv icon

Semantic loss guided data efficient supervised fine tuning for Safe Responses in LLMs

Add code
Dec 07, 2024
Viaarxiv icon

UNIQ: Offline Inverse Q-learning for Avoiding Undesirable Demonstrations

Add code
Oct 10, 2024
Viaarxiv icon

Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans

Add code
Jul 24, 2024
Figure 1 for Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
Figure 2 for Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
Figure 3 for Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
Figure 4 for Towards Neural Network based Cognitive Models of Dynamic Decision-Making by Humans
Viaarxiv icon

Preserving the Privacy of Reward Functions in MDPs through Deception

Add code
Jul 13, 2024
Viaarxiv icon

Safety through feedback in Constrained RL

Add code
Jun 28, 2024
Viaarxiv icon