8 papers · 1 filter
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…
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…
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…
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…
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…
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…