Related papers: Q-Probe: A Lightweight Approach to Reward Maximiza…

In many sequential decision-making problems (e.g., robotics control, game playing, sequential prediction), human or expert data is available containing useful information about the task. However, imitation learning (IL) from a small amount…

With the rapid growth in the use of fine-tuning for large language models (LLMs), optimizing fine-tuning while keeping inference efficient has become highly important. However, this is a challenging task as it requires improvements in all…

Applying Q-learning to high-dimensional or continuous action spaces can be difficult due to the required maximization over the set of possible actions. Motivated by techniques from amortized inference, we replace the expensive maximization…

Q-learning is a stochastic approximation version of the classic value iteration. The literature has established that Q-learning suffers from both maximization bias and slower convergence. Recently, multi-step algorithms have shown practical…

The $Q$-learning algorithm is a simple and widely-used stochastic approximation scheme for reinforcement learning, but the basic protocol can exhibit instability in conjunction with function approximation. Such instability can be observed…

Current soft prompt methods yield limited performance when applied to small-sized models (fewer than a billion parameters). Deep prompt-tuning, which entails prepending parameters in each layer for enhanced efficacy, presents a solution for…

Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function. However, these methods generally require implicit reward regularization to improve stability…

Recent advances have shown that optimizing prompts for Large Language Models (LLMs) can significantly improve task performance, yet many optimization techniques rely on heuristics or manual exploration. We present LatentPrompt, a…

To ensure that large language model (LLM) responses are helpful and non-toxic, a reward model trained on human preference data is usually used. LLM responses with high rewards are then selected through best-of-$n$ (BoN) sampling or the LLM…

Various algorithms in reinforcement learning exhibit dramatic variability in their convergence rates and ultimate accuracy as a function of the problem structure. Such instance-specific behavior is not captured by existing global minimax…

The progress introduced by pre-trained language models and their fine-tuning has resulted in significant improvements in most downstream NLP tasks. The unsupervised training of a language model combined with further target task fine-tuning…

Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that…

Model-free reinforcement learning (RL) algorithms, such as Q-learning, directly parameterize and update value functions or policies without explicitly modeling the environment. They are typically simpler, more flexible to use, and thus more…

Knowledge enhanced pre-trained language models (K-PLMs) are shown to be effective for many public tasks in the literature but few of them have been successfully applied in practice. To address this problem, we propose K-AID, a systematic…

Even though large language models are becoming increasingly capable, it is still unreasonable to expect them to excel at tasks that are under-represented on the Internet. Leveraging LLMs for specialized applications, particularly in niche…

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

There is a growing desire in the field of reinforcement learning (and machine learning in general) to move from black-box models toward more "interpretable AI." We improve interpretability of reinforcement learning by increasing the utility…

Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sarsa) algorithms are efficient and frequently used techniques in reinforcement learning. Q$(\sigma,\lambda)$ is the first approach unifies them with eligibility trace…

Reinforcement learning from human feedback (RLHF) has emerged as an effective approach to aligning large language models (LLMs) to human preferences. RLHF contains three steps, i.e., human preference collecting, reward learning, and policy…

Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing. However, this training objective is inconsistent with…