Related papers: Understanding the performance gap between online a…
Re-inforcement learning from human feedback (RLHF) has been effective in the task of AI alignment. However, one of the key assumptions of RLHF is that the annotators (referred to as workers from here on out) have a homogeneous response…
Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models. InstructGPT implements RLHF through…
Supervised imitation-based approaches are often favored over off-policy reinforcement learning approaches for learning policies offline, since their straightforward optimization objective makes them computationally efficient and stable to…
Reinforcement Learning from Human Feedback (RLHF) has become a cornerstone technique for post-training large language models. While most existing approaches rely on the reverse KL-regularization, recent empirical studies have begun…
We consider the problem of offline reinforcement learning from human feedback (RLHF) with pairwise comparisons proposed by Zhu et al. (2023), where the implicit reward is a linear function of an unknown parameter. Given an offline dataset,…
Reinforcement learning (RL) algorithms are often categorized as either on-policy or off-policy depending on whether they use data from a target policy of interest or from a different behavior policy. In this paper, we study a subtle…
Off-policy evaluation (OPE) is important for closing the gap between offline training and evaluation of reinforcement learning (RL), by estimating performance and/or rank of target (evaluation) policies using offline trajectories only. It…
Reinforcement Learning from Human Feedback (RLHF) aligns Large Language Models (LLMs) with human preferences, yet the underlying reward signals they internalize remain hidden, posing a critical challenge for interpretability and safety.…
State-of-the-art large language models (LLMs) have become indispensable tools for various tasks. However, training LLMs to serve as effective assistants for humans requires careful consideration. A promising approach is reinforcement…
Sequential decision-making agents struggle with long horizon tasks, since solving them requires multi-step reasoning. Most reinforcement learning (RL) algorithms address this challenge by improved credit assignment, introducing memory…
Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…
This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agent are contingent on a particular way of behaving,…
Reinforcement learning (RL) approaches for Large Language Models (LLMs) frequently use on-policy algorithms, such as PPO or GRPO. However, policy lag from distributed training architectures and differences between the training and inference…
Reinforcement learning with human feedback (RLHF), as a widely adopted approach in current large language model pipelines, is \textit{bottlenecked by the size of human preference data}. While traditional methods rely on offline preference…
In this work, we argue for the importance of an online evaluation budget for a reliable comparison of deep offline RL algorithms. First, we delineate that the online evaluation budget is problem-dependent, where some problems allow for less…
Reinforcement Learning from Human Feedback (RLHF) has enabled significant advancements within language modeling for powerful, instruction-following models. However, the alignment of these models remains a pressing challenge as the policy…
We investigate the effectiveness of reinforcement learning methods for finetuning large language models when transitioning from offline to semi-online to fully online regimes for both verifiable and non-verifiable tasks. Our experiments…
The objective of offline RL is to learn optimal policies when a fixed exploratory demonstrations data-set is available and sampling additional observations is impossible (typically if this operation is either costly or rises ethical…
Reinforcement learning from human feedback (RLHF) is a technique for training AI systems to align with human goals. RLHF has emerged as the central method used to finetune state-of-the-art large language models (LLMs). Despite this…
Faithfulness, expressiveness, and elegance is the constant pursuit in machine translation. However, traditional metrics like \textit{BLEU} do not strictly align with human preference of translation quality. In this paper, we explore…