activity
20242026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Scenario Generation for Risk-Aware Reinforcement Learning with Probably Approximately Safe Guarantees

Mohit Prashant, Arvind Easwaran

Guaranteeing safety is critical to the deployment of reinforcement learning (RL) agents in the real-world, especially as policies learned using deep RL may demonstrate susceptibili…

cs.LG2026

Approximation-Free Differentiable Oblique Decision Trees

Subrat Prasad Panda, Blaise Genest, Arvind Easwaran

Decision Trees (DTs) are widely used in safety-critical domains such as medical diagnosis, valued for their interpretability and effectiveness on tabular data. However, training ac…

cs.LG2025

Disentangled and Distilled Encoder for Out-of-Distribution Reasoning with Rademacher Guarantees

Zahra Rahiminasab, Michael Yuhas, Arvind Easwaran

Recently, the disentangled latent space of a variational autoencoder (VAE) has been used to reason about multi-label out-of-distribution (OOD) test samples that are derived from di…

cs.LG2025

Improving Reinforcement Learning Sample-Efficiency using Local Approximation

Mohit Prashant, Arvind Easwaran

In this study, we derive Probably Approximately Correct (PAC) bounds on the asymptotic sample-complexity for RL within the infinite-horizon Markov Decision Process (MDP) setting th…

cs.LG2025

CRLLK: Constrained Reinforcement Learning for Lane Keeping in Autonomous Driving

Xinwei Gao, Arambam James Singh, Gangadhar Royyuru +2

Lane keeping in autonomous driving systems requires scenario-specific weight tuning for different objectives. We formulate lane-keeping as a constrained reinforcement learning prob…

cs.LG2025

Guaranteeing Out-Of-Distribution Detection in Deep RL via Transition Estimation

Mohit Prashant, Arvind Easwaran, Suman Das +1

An issue concerning the use of deep reinforcement learning (RL) agents is whether they can be trusted to perform reliably when deployed, as training environments may not reflect re…