Related papers: Random Reward Phase-Type Distributions with Applic…
Though significant advancements have been achieved in developing long-context large language models (LLMs), the compromised quality of LLM-synthesized data for supervised fine-tuning (SFT) often affects the long-context performance of SFT…
We study the model-based reward-free reinforcement learning with linear function approximation for episodic Markov decision processes (MDPs). In this setting, the agent works in two phases. In the exploration phase, the agent interacts with…
All reinforcement learning algorithms must handle the trade-off between exploration and exploitation. Many state-of-the-art deep reinforcement learning methods use noise in the action selection, such as Gaussian noise in policy gradient…
We present Direct Reward Fine-Tuning (DRaFT), a simple and effective method for fine-tuning diffusion models to maximize differentiable reward functions, such as scores from human preference models. We first show that it is possible to…
In this paper we consider reinforcement learning tasks with progressive rewards; that is, tasks where the rewards tend to increase in magnitude over time. We hypothesise that this property may be problematic for value-based deep…
The class of $\alpha$-stable distributions received much interest for modelling impulsive phenomena occur in engineering, economics, insurance, and physics. The lack of non-analytical form for probability density function is considered as…
We study reward-free and reward-agnostic exploration in episodic finite-horizon Markov decision processes (MDPs), where an agent explores an unknown environment without observing external rewards. Reward-free exploration aims to enable…
Dealing with environments with sparse rewards has always been crucial for systems developed to operate in autonomous open-ended learning settings. Intrinsic Motivations could be an effective way to help Deep Reinforcement Learning…
Test-time reinforcement learning (TTRL) enables large language models (LLMs) to self-improve on unlabeled inputs, but its effectiveness critically depends on how reward signals are estimated without ground-truth supervision. Most existing…
Downscaling techniques are one of the most prominent applications of Deep Learning (DL) in Earth System Modeling. A robust DL downscaling model can generate high-resolution fields from coarse-scale numerical model simulations, saving the…
We introduce Random Reward Perturbation (RRP), a novel exploration strategy for reinforcement learning (RL). Our theoretical analyses demonstrate that adding zero-mean noise to environmental rewards effectively enhances policy diversity…
The Rasch model is one of the most fundamental models in \emph{item response theory} and has wide-ranging applications from education testing to recommendation systems. In a universe with $n$ users and $m$ items, the Rasch model assumes…
Many continuous control problems can be formulated as sparse-reward reinforcement learning (RL) tasks. In principle, online RL methods can automatically explore the state space to solve each new task. However, discovering sequences of…
One major limitation to the applicability of Reinforcement Learning (RL) to many practical domains is the large number of samples required to learn an optimal policy. To address this problem and improve learning efficiency, we consider a…
Major depressive disorder (MDD), a leading cause of disability and mortality, is associated with reward-processing abnormalities and concentration issues. Motivated by the probabilistic reward task from the Establishing Moderators and…
Data collected from wearable devices and smartphones can shed light on an individual's pattern of behavioral and circadian routine. Phone use can be modeled as alternating event process, between the state of active use and the state of…
When a person is not satisfied with how a robot performs a task, they can intervene to correct it. Reward learning methods enable the robot to adapt its reward function online based on such human input, but they rely on handcrafted…
A novel model of intermittency is presented in which the dynamics of the rates of energy transfer between successive steps in the energy cascade is described by a hierarchy of stochastic differential equations. The probability distribution…
Exploring in environments with high-dimensional observations is hard. One promising approach for exploration is to use intrinsic rewards, which often boils down to estimating "novelty" of states, transitions, or trajectories with deep…
In this paper we introduce a bivariate distribution on $\mathbb{R}_{+} \times \mathbb{N}$ arising from a single underlying Markov jump process. The marginal distributions are phase-type and discrete phase-type distributed, respectively,…