Search Results for author:
Found 13 papers, 4 papers with code
Offline Regularised Reinforcement Learning for Large Language Models Alignment
The canonical element of such datasets is for instance an LLM's response to a user's prompt followed by a user's feedback such as a thumbs-up/down.
Embedding-Aligned Language Models
Our embedding-aligned guided language (EAGLE) agent is trained to iteratively steer the LLM's generation towards optimal regions of the latent embedding space, w. r. t.
Multi-turn Reinforcement Learning from Preference Human Feedback
Reinforcement Learning from Human Feedback (RLHF) has become the standard approach for aligning Large Language Models (LLMs) with human preferences, allowing LLMs to demonstrate remarkable abilities in various tasks.
Demystifying Embedding Spaces using Large Language Models
Embeddings have become a pivotal means to represent complex, multi-faceted information about entities, concepts, and relationships in a condensed and useful format.
Factually Consistent Summarization via Reinforcement Learning with Textual Entailment Feedback
Despite the seeming success of contemporary grounded text generation systems, they often tend to generate factually inconsistent text with respect to their input.
Abstractive Text Summarization
Natural Language Inference
+3
Reinforcement Learning with History-Dependent Dynamic Contexts
We introduce Dynamic Contextual Markov Decision Processes (DCMDPs), a novel reinforcement learning framework for history-dependent environments that generalizes the contextual MDP framework to handle non-Markov environments, where contexts change over time.
Reinforcement Learning with a Terminator
We learn the parameters of the TerMDP and leverage the structure of the estimation problem to provide state-wise confidence bounds.
Online Apprenticeship Learning
Finally, we implement a deep variant of our algorithm which shares some similarities to GAIL \cite{ho2016generative}, but where the discriminator is replaced with the costs learned by the OAL problem.
Mirror Descent Policy Optimization
Overall, MDPO is derived from the MD principles, offers a unified approach to viewing a number of popular RL algorithms, and performs better than or on-par with TRPO, PPO, and SAC in a number of continuous control tasks.
Optimistic Policy Optimization with Bandit Feedback
To the best of our knowledge, the two results are the first sub-linear regret bounds obtained for policy optimization algorithms with unknown transitions and bandit feedback.
Adaptive Trust Region Policy Optimization: Global Convergence and Faster Rates for Regularized MDPs
Trust region policy optimization (TRPO) is a popular and empirically successful policy search algorithm in Reinforcement Learning (RL) in which a surrogate problem, that restricts consecutive policies to be 'close' to one another, is iteratively solved.
Multi Instance Learning For Unbalanced Data
In the context of Multi Instance Learning, we analyze the Single Instance (SI) learning objective.
Exploration Conscious Reinforcement Learning Revisited
We continue and analyze properties of exploration-conscious optimal policies and characterize two general approaches to solve such criteria.
