Search Results for author:
Found 10 papers, 4 papers with code
RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
A promising approach is reinforcement learning from human feedback (RLHF), which leverages human feedback to update the model in accordance with human preferences and mitigate issues like toxicity and hallucinations.
Gradient Networks
Our analysis leads to two distinct GradNet architectures, GradNet-C and GradNet-M, and we describe the corresponding monotone versions, mGradNet-C and mGradNet-M. Our empirical results show that these architectures offer efficient parameterizations and outperform popular methods in gradient field learning tasks.
From Past to Future: Rethinking Eligibility Traces
In this paper, we introduce a fresh perspective on the challenges of credit assignment and policy evaluation.
Distributional Off-Policy Evaluation for Slate Recommendations
Prior work has developed estimators that leverage the structure in slates to estimate the expected off-policy performance, but the estimation of the entire performance distribution remains elusive.
Learning Gradients of Convex Functions with Monotone Gradient Networks
While much effort has been devoted to deriving and analyzing effective convex formulations of signal processing problems, the gradients of convex functions also have critical applications ranging from gradient-based optimization to optimal transport.
High-Resolution CMB Lensing Reconstruction with Deep Learning
Next-generation cosmic microwave background (CMB) surveys are expected to provide valuable information about the primordial universe by creating maps of the mass along the line of sight.
Generative Adversarial Network
Vocal Bursts Intensity Prediction
Unsupervised Clustering of Time Series Signals using Neuromorphic Energy-Efficient Temporal Neural Networks
Unsupervised time series clustering is a challenging problem with diverse industrial applications such as anomaly detection, bio-wearables, etc.
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
Building off of a probabilistic view of RL, we formally show that we can achieve this goal by compensating for the difference in dynamics by modifying the reward function.
Multi-Armed Bandits with Correlated Arms
We consider a multi-armed bandit framework where the rewards obtained by pulling different arms are correlated.
A Unified Approach to Translate Classical Bandit Algorithms to the Structured Bandit Setting
We consider a finite-armed structured bandit problem in which mean rewards of different arms are known functions of a common hidden parameter $\theta^*$.
