Related papers: Understanding Generalization in Role-Playing Model…
Model-based reinforcement learning (RL) algorithms allow us to combine model-generated data with those collected from interaction with the real system in order to alleviate the data efficiency problem in RL. However, designing such…
Information retrieval aims to find information that meets users' needs from the corpus. Different needs correspond to different IR tasks such as document retrieval, open-domain question answering, retrieval-based dialogue, etc., while they…
The $\ell_0$-constrained empirical risk minimization ($\ell_0$-ERM) is a promising tool for high-dimensional statistical estimation. The existing analysis of $\ell_0$-ERM estimator is mostly on parameter estimation and support recovery…
Ensuring generalization to unseen environments remains a challenge. Domain shift can lead to substantially degraded performance unless shifts are well-exercised within the available training environments. We introduce a simple robust…
As AI systems become more intelligent and their behavior becomes more challenging to assess, they may learn to game the flaws of human feedback instead of genuinely striving to follow instructions; however, this risk can be mitigated by…
Model-based reinforcement learning (RL) is more sample efficient than model-free RL by using imaginary trajectories generated by the learned dynamics model. When the model is inaccurate or biased, imaginary trajectories may be deleterious…
A key challenge in e-learning environments like Intelligent Tutoring Systems (ITSs) is to induce effective pedagogical policies efficiently. While Deep Reinforcement Learning (DRL) often suffers from sample inefficiency and reward function…
Theory of Mind (ToM) is the ability to understand and reflect on the mental states of others. Although this capability is crucial for human interaction, testing on Large Language Models (LLMs) reveals that they possess only a rudimentary…
Empirical risk minimization (ERM) is a fundamental machine learning paradigm. However, its generalization ability is limited in various tasks. In this paper, we devise Dummy Risk Minimization (DuRM), a frustratingly easy and general…
Reinforcement learning (RL) typically models the interaction between the agent and environment as a Markov decision process (MDP), where the rewards that guide the agent's behavior are always observable. However, in many real-world…
This paper extends recent work in interactive machine learning (IML) focused on effectively incorporating human feedback. We show how control and feedback signals complement each other in systems which model human reward. We demonstrate…
We study the benefits of reinforcement learning (RL) environments based on agent-based models (ABM). While ABMs are known to offer microfoundational simulations at the cost of computational complexity, we empirically show in this work that…
Reinforcement learning has demonstrated impressive performance in various challenging problems such as robotics, board games, and classical arcade games. However, its real-world applications can be hindered by the absence of robustness and…
The success of AI assistants based on language models (LLMs) hinges crucially on Reinforcement Learning from Human Feedback (RLHF), which enables the generation of responses more aligned with human preferences. As universal AI assistants,…
During the preference optimization of large language models (LLMs), distribution shifts may arise between newly generated model samples and the data used to train the reward model (RM). This shift reduces the efficacy of the RM, which in…
We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a data representation such that the optimal classifier, on top…
Large language models (LLMs) deployed as agents solve user-specified tasks over multiple steps while keeping the required manual engagement to a minimum. Crucially, such LLMs need to ground their generations in any feedback obtained to…
The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments. Increasing the generalization capacity of the RL systems can…
Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic errors. A promising solution is reinforcement learning (RL)…
The performance of Large Language Models (LLMs) often degrades when crucial information is in the middle of a long context, a "lost-in-the-middle" phenomenon that mirrors the primacy and recency effects in human memory. We propose that this…