Rishabh Agarwal

9

Papers

43

Total Citations

Papers (9)

Inference-Aware Fine-Tuning for Best-of-N Sampling in Large Language Models

SiT: Symmetry-invariant Transformers for Generalisation in Reinforcement Learning

Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning

Neural Additive Models: Interpretable Machine Learning with Neural Nets

Deep Reinforcement Learning at the Edge of the Statistical Precipice

Reincarnating Reinforcement Learning: Reusing Prior Computation to Accelerate Progress

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

Learning to Generalize from Sparse and Underspecified Rewards