7 papers
Learning the ARTS of Search for Automated Discovery
Gurusha Juneja, Arnav Kumar Jain, Deepak Nathani +2
Scientific discovery can be formulated as an iterative search process over the space of hypotheses and experiments. Contemporary methods navigate this space using heuristics such a…
WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation
Arnav Kumar Jain, Yilin Wu, Jesse Farebrother +2
The potential impacts of world models (WMs, i.e., learned simulators) on robotics are far-reaching -- policy evaluation, policy improvement, and test-time planning -- all with limi…
A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search
Arnav Kumar Jain, Vibhakar Mohta, Subin Kim +5
The fundamental limitation of the behavioral cloning (BC) approach to imitation learning is that it only teaches an agent what the expert did at states the expert visited. This mea…
An Explainable Deep Neural Network with Frequency-Aware Channel and Spatial Refinement for Flood Prediction in Sustainable Cities
Shahid Shafi Dar, Bharat Kaurav, Arnav Jain +3
In an era of escalating climate change, urban flooding has emerged as a critical challenge for sustainable cities, threatening lives, infrastructure, and ecosystems. Traditional fl…
Multi-Turn Code Generation Through Single-Step Rewards
Arnav Kumar Jain, Gonzalo Gonzalez-Pumariega, Wayne Chen +3
We address the problem of code generation from multi-turn execution feedback. Existing methods either generate code without feedback or use complex, hierarchical reinforcement lear…
Non-Adversarial Inverse Reinforcement Learning via Successor Feature Matching
Arnav Kumar Jain, Harley Wiltzer, Jesse Farebrother +3
In inverse reinforcement learning (IRL), an agent seeks to replicate expert demonstrations through interactions with the environment. Traditionally, IRL is treated as an adversaria…