arXiv research

Paper introduces PRMs to learn non-Markovian stochastic rewards for reinforcement learning.

Efficient RL in PRMs with improved regret bound.

Scalable model for slate recommendation learns reward probabilities.

Integration of reinforcement learning and imitation learning is an important problem that has been studied for a long time in the field of intelligent robotics. Reinforcement learning optimizes policies to maximize the cumulative reward, whereas imitation learning attempts to extract general knowledge about the traject…

New algorithm minimizes regret in multi-agent bandit problem with probabilistic communication.

RePULSe improves language model alignment by reducing undesired outputs without sacrificing overall performance.

This paper tackles distribution shift in model-based offline RL, proposing a shifts-aware reward method.

Enhances reward specification in RL with a novel language-based approach.

New RL approach infers optimal policies via variational inference.

Probabilistic ML improves healthcare data analysis.

This paper explores the possibility of near-optimally solving multi-agent, multi-task NP-hard planning problems with time-dependent rewards using a learning-based algorithm. In particular, we consider a class of robot/machine scheduling problems called the multi-robot reward collection problem (MRRC). Such MRRC problem…

The paper examines how updates to probabilistic models influence behavior based on evidence.

New algorithm uses machine learning to predict rewards for decision-making problems.

Generative flow networks use RL to learn probabilistic models efficiently.

We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability $p_{ij}$. Two cases are covered. (a) The one-step case, where after playing arm $i$ the learner observes a sample reward feedback of arm $j$ with independent prob…

New scoring rules improve probabilistic classification model evaluation.

Providing a suitable reward function to reinforcement learning can be difficult in many real world applications. While inverse reinforcement learning (IRL) holds promise for automatically learning reward functions from demonstrations, several major challenges remain. First, existing IRL methods learn reward functions f…

A new method for reinforcement learning that adapts to different domains using auxiliary classifiers.

The paper proposes a model reward scheme for collaborative ML based on Shapley value and information gain.

Paper shows RLHF can be solved similarly to standard RL.

RLMH improves adaptive MCMC by optimizing contrastive divergence reward.

LinConTS improves regret and constraint violations in probabilistic linearly constrained bandits.

Discusses new probabilistic morphisms and geometric methods in machine and statistical learning.

Unified approach to path planning using probabilistic inference on factor graphs.

PGBM creates probabilistic predictions efficiently.

Extends PCVM for multi-class classification with improved accuracy.

Inverse optimal control, also known as inverse reinforcement learning, is the problem of recovering an unknown reward function in a Markov decision process from expert demonstrations of the optimal policy. We introduce a probabilistic inverse optimal control algorithm that scales gracefully with task dimensionality, an…

Paper explores limits and possibilities of aligning LLMs with human preferences.

Reinforcement learning is a promising framework for solving control problems, but its use in practical situations is hampered by the fact that reward functions are often difficult to engineer. Specifying goals and tasks for autonomous machines, such as robots, is a significant challenge: conventionally, reward function…

EOI enhances individuality in multi-agent systems.

Probabilistic models can handle causal inference without special tools.

New algorithm optimizes for long-term user satisfaction in delayed reward settings.

Paper quantifies uncertainty in probabilistic models using Gaussian Processes.

Study introduces TeMoP model for better stock market predictions.

New algorithm robust to probabilistic unbounded adversarial attacks in bandit problems.

Probabilistic programming is a powerful abstraction for statistical machine learning. Applying static analysis methods to probabilistic programs could serve to optimize the learning process, automatically verify properties of models, and improve the programming interface for users. This field of static analysis for pro…

Robots need models of human behavior for both inferring human goals and preferences, and predicting what people will do. A common model is the Boltzmann noisily-rational decision model, which assumes people approximately optimize a reward function and choose trajectories in proportion to their exponentiated reward. Whi…

Training-free method improves large language model sequence quality via reward-guided sampling.

Develops probabilistic safety regions for scalable classifiers.

A new neural network model MDRBM improves noise-robustness in classification.

Transfer learning improves sparse, interpretable probabilistic classification.

Modeling decision-making dynamics in MDD patients using RL-HMM.

Enhances GFlowNets with distributional approach for risk-sensitive policies.

Proposes a cost-sensitive method to generate probabilistic SVM outputs.

$\textit{Pymc-learn}$ is a Python package providing a variety of state-of-the-art probabilistic models for supervised and unsupervised machine learning. It is inspired by $\textit{scikit-learn}$ and focuses on bringing probabilistic machine learning to non-specialists. It uses a general-purpose high-level language that…

The paper presents a probabilistic framework for SPD matrices in machine learning.

This thesis proposes a derivatives hedging framework using deep learning and reinforcement learning.

Study on reward poisoning attacks on CMAB, revealing attackability depends on adversary's knowledge.