2 citations · 2 across the 6 of their papers we have counts for
7 papers
Convex-Concave Reinforcement Learning
Shripad V. Deshmukh, Yaswanth Chittepu, Dhawal Gupta +2
Policy learning drives many of the most consequential and heavily-invested applications of reinforcement learning today. Yet the core optimization problem it rests on (maximizing e…
Mitigating Preference Hacking in Policy Optimization with Pessimism
Dhawal Gupta, Adam Fisch, Christoph Dann +1
This work tackles the problem of overoptimization in reinforcement learning from human feedback (RLHF), a prevalent technique for aligning models with human preferences. RLHF relie…
A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments
Erfan Entezami, Mahsa Sahebdel, Dhawal Gupta
Training a model-free reinforcement learning agent requires allowing the agent to sufficiently explore the environment to search for an optimal policy. In safety-constrained enviro…
ICU-Sepsis: A Benchmark MDP Built from Real Medical Data
Kartik Choudhary, Dhawal Gupta, Philip S. Thomas
We present ICU-Sepsis, an environment that can be used in benchmarks for evaluating reinforcement learning (RL) algorithms. Sepsis management is a complex task that has been an imp…
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…
Behavior Alignment via Reward Function Optimization
Dhawal Gupta, Yash Chandak, Scott M. Jordan +2
Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identif…
Exploring the impact of low-rank adaptation on the performance, efficiency, and regularization of RLHF
Simeng Sun, Dhawal Gupta, Mohit Iyyer
During the last stage of RLHF, a large language model is aligned to human intents via PPO training, a process that generally requires large-scale computational resources. In this t…