Search Results for author:
Found 8 papers, 6 papers with code
REBEL: Reinforcement Learning via Regressing Relative Rewards
While originally developed for continuous control problems, Proximal Policy Optimization (PPO) has emerged as the work-horse of a variety of reinforcement learning (RL) applications including the fine-tuning of generative models.
Adversarial Imitation Learning via Boosting
In the weighted replay buffer, the contribution of the data from older policies are properly discounted with the weight computed based on the boosting framework.
Dataset Reset Policy Optimization for RLHF
Motivated by the fact that offline preference dataset provides informative states (i. e., data that is preferred by the labelers), our new algorithm, Dataset Reset Policy Optimization (DR-PO), integrates the existing offline preference dataset into the online policy training procedure via dataset reset: it directly resets the policy optimizer to the states in the offline dataset, instead of always starting from the initial state distribution.
RL for Consistency Models: Faster Reward Guided Text-to-Image Generation
To overcome this limitation, consistency models proposed learning a new class of generative models that directly map noise to data, resulting in a model that can generate an image in as few as one sampling iteration.
Policy-Gradient Training of Language Models for Ranking
Text retrieval plays a crucial role in incorporating factual knowledge for decision making into language processing pipelines, ranging from chat-based web search to question answering systems.
Learning to Generate Better Than Your LLM
In particular, we extend RL algorithms to allow them to interact with a dynamic black-box guide LLM and propose RL with guided feedback (RLGF), a suite of RL algorithms for LLM fine-tuning.
Learning Bellman Complete Representations for Offline Policy Evaluation
We study representation learning for Offline Reinforcement Learning (RL), focusing on the important task of Offline Policy Evaluation (OPE).
Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage
Instead, the learner is presented with a static offline dataset of state-action-next state transition triples from a potentially less proficient behavior policy.
