10 citations · 15 across the 8 of their papers we have counts for
8 papers
RRISE: Robust Radius Inference via a Surrogate Estimator
Jong-Ik Park, Shreyas Chaudhari, Carlee Joe-Wong +1
Randomized smoothing (RS) uses a smoothed classifier to provide architecture-agnostic certificates of classification robustness, but its dependence on per-input Monte Carl…
Which Rewards Matter? Reward Selection for Reinforcement Learning under Limited Feedback
Shreyas Chaudhari, Renhao Zhang, Philip S. Thomas +1
The ability of reinforcement learning algorithms to learn effective policies is determined by the rewards available during training. However, for practical problems, obtaining larg…
Probing AI Safety with Source Code
Ujwal Narayan, Shreyas Chaudhari, Ashwin Kalyan +4
Large language models (LLMs) have become ubiquitous, interfacing with humans in numerous safety-critical applications. This necessitates improving capabilities, but importantly cou…
Agent Context Protocols Enhance Collective Inference
Devansh Bhardwaj, Arjun Beniwal, Shreyas Chaudhari +5
AI agents have become increasingly adept at complex tasks such as coding, reasoning, and multimodal understanding. However, building generalist systems requires moving beyond indiv…
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation
Shreyas Chaudhari, Ameet Deshpande, Bruno Castro da Silva +1
Evaluating policies using off-policy data is crucial for applying reinforcement learning to real-world problems such as healthcare and autonomous driving. Previous methods for off-…
PersonaGym: Evaluating Persona Agents and LLMs
Vinay Samuel, Henry Peng Zou, Yue Zhou +6
Persona agents, which are LLM agents conditioned to act according to an assigned persona, enable contextually rich and user aligned interactions across domains like education and h…
RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
Shreyas Chaudhari, Pranjal Aggarwal, Vishvak Murahari +5
State-of-the-art large language models (LLMs) have become indispensable tools for various tasks. However, training LLMs to serve as effective assistants for humans requires careful…
From Past to Future: Rethinking Eligibility Traces
Dhawal Gupta, Scott M. Jordan, Shreyas Chaudhari +3
In this paper, we introduce a fresh perspective on the challenges of credit assignment and policy evaluation. First, we delve into the nuances of eligibility traces and explore ins…