22 citations · 85 across the 31 of their papers we have counts for
27 papers · 1 filter
Short-Long Policy Evaluation with Novel Actions
Hyunji Alex Nam, Yash Chandak, Emma Brunskill
From incorporating LLMs in education, to identifying new drugs and improving ways to charge batteries, innovators constantly try new strategies in search of better long-term outcom…
Averaging log-likelihoods in direct alignment
Nathan Grinsztajn, Yannis Flet-Berliac, Mohammad Gheshlaghi Azar +8
To better align Large Language Models (LLMs) with human judgment, Reinforcement Learning from Human Feedback (RLHF) learns a reward model and then optimizes it using regularized RL…
Contrastive Policy Gradient: Aligning LLMs on sequence-level scores in a supervised-friendly fashion
Yannis Flet-Berliac, Nathan Grinsztajn, Florian Strub +8
Reinforcement Learning (RL) has been used to finetune Large Language Models (LLMs) using a reward model trained from preference data, to better align with human judgment. The recen…
OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
Allen Nie, Yash Chandak, Christina J. Yuan +3
Offline policy evaluation (OPE) allows us to evaluate and estimate a new sequential decision-making policy's performance by leveraging historical interaction data collected from ot…
A/B testing under Interference with Partial Network Information
Shiv Shankar, Ritwik Sinha, Yash Chandak +2
A/B tests are often required to be conducted on subjects that might have social connections. For e.g., experiments on social media, or medical and social interventions to control t…
Adaptive Instrument Design for Indirect Experiments
Yash Chandak, Shiv Shankar, Vasilis Syrgkanis +1
Indirect experiments provide a valuable framework for estimating treatment effects in situations where conducting randomized control trials (RCTs) is impractical or unethical. Unli…
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…
Supervised Pretraining Can Learn In-Context Reinforcement Learning
Jonathan N. Lee, Annie Xie, Aldo Pacchiano +4
Large transformer models trained on diverse datasets have shown a remarkable ability to learn in-context, achieving high few-shot performance on tasks they were not explicitly trai…
Coagent Networks: Generalized and Scaled
James E. Kostas, Scott M. Jordan, Yash Chandak +5
Coagent networks for reinforcement learning (RL) [Thomas and Barto, 2011] provide a powerful and flexible framework for deriving principled learning rules for arbitrary stochastic…
Representations and Exploration for Deep Reinforcement Learning using Singular Value Decomposition
Yash Chandak, Shantanu Thakoor, Zhaohan Daniel Guo +4
Representation learning and exploration are among the key challenges for any deep reinforcement learning agent. In this work, we provide a singular value decomposition based method…
Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments
Vincent Liu, Yash Chandak, Philip Thomas +1
In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data i…
Optimization using Parallel Gradient Evaluations on Multiple Parameters
Yash Chandak, Shiv Shankar, Venkata Gandikota +2
We propose a first-order method for convex optimization, where instead of being restricted to the gradient from a single parameter, gradients from multiple parameters can be used d…
Off-Policy Evaluation for Action-Dependent Non-Stationary Environments
Yash Chandak, Shiv Shankar, Nathaniel D. Bastian +3
Methods for sequential decision-making are often built upon a foundational assumption that the underlying decision process is stationary. This limits the application of such method…
Understanding Self-Predictive Learning for Reinforcement Learning
Yunhao Tang, Zhaohan Daniel Guo, Pierre Harvey Richemond +13
We study the learning dynamics of self-predictive learning for reinforcement learning, a family of algorithms that learn representations by minimizing the prediction error of their…
SOPE: Spectrum of Off-Policy Estimators
Christina J. Yuan, Yash Chandak, Stephen Giguere +2
Many sequential decision making problems are high-stakes and require off-policy evaluation (OPE) of a new policy using historical data collected using some other policy. One of the…
Universal Off-Policy Evaluation
Yash Chandak, Scott Niekum, Bruno Castro da Silva +3
When faced with sequential decision-making problems, it is often useful to be able to predict what would happen if decisions were made using a new policy. Those predictions must of…
High-Confidence Off-Policy (or Counterfactual) Variance Estimation
Yash Chandak, Shiv Shankar, Philip S. Thomas
Many sequential decision-making systems leverage data collected using prior policies to propose a new policy. For critical applications, it is important that high-confidence guaran…
Towards Safe Policy Improvement for Non-Stationary MDPs
Yash Chandak, Scott M. Jordan, Georgios Theocharous +2
Many real-world sequential decision-making problems involve critical systems with financial risks and human-life risks. While several works in the past have proposed methods that a…
Reinforcement Learning for Strategic Recommendations
Georgios Theocharous, Yash Chandak, Philip S. Thomas +1
Strategic recommendations (SR) refer to the problem where an intelligent agent observes the sequential behaviors and activities of users and decides when and how to interact with t…
Evaluating the Performance of Reinforcement Learning Algorithms
Scott M. Jordan, Yash Chandak, Daniel Cohen +2
Performance evaluations are critical for quantifying algorithmic advances in reinforcement learning. Recent reproducibility analyses have shown that reported performance results ar…
Optimizing for the Future in Non-Stationary MDPs
Yash Chandak, Georgios Theocharous, Shiv Shankar +3
Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process i…
Classical Policy Gradient: Preserving Bellman's Principle of Optimality
Philip S. Thomas, Scott M. Jordan, Yash Chandak +2
We propose a new objective function for finite-horizon episodic Markov decision processes that better captures Bellman's principle of optimality, and provide an expression for the…
Reinforcement Learning When All Actions are Not Always Available
Yash Chandak, Georgios Theocharous, Blossom Metevier +1
The Markov decision process (MDP) formulation used to model many real-world sequential decision making problems does not efficiently capture the setting where the set of available…
Lifelong Learning with a Changing Action Set
Yash Chandak, Georgios Theocharous, Chris Nota +1
In many real-world sequential decision making problems, the number of available actions (decisions) can vary over time. While problems like catastrophic forgetting, changing transi…