arXiv research

Proof of convergence for multi-objective optimization using inverse reinforcement learning.

Proof shows imitation of expert's reward and solutions in multi-objective optimization.

This paper introduces a new scalable multi-objective deep reinforcement learning (MODRL) framework based on deep Q-networks. We develop a high-performance MODRL framework that supports both single-policy and multi-policy strategies, as well as both linear and non-linear approaches to action selection. The experimental …

The paper explores a Multi-Objective RL approach for trading that generalizes reward functions.

Deep learning agent improves pedestrian navigation in urban environments.

Paper tackles multi-object reinforcement learning, improving skill extrapolation.

Proposes a novel algorithm for multi-objective reinforcement learning.

Develops a new method to improve performance in multi-objective learning problems.

This work overcomes bias in concave multi-objective reinforcement learning.

Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for finding a good balance between these components by searching for the optimal re…

A framework for data-driven decision-making in infectious disease control.

Paper tackles regret bounds and exploration complexity for multi-objective reinforcement learning with picky preferences.

Proposes new stochastic algorithms for multi-objective optimization.

Many real-world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as a tabular Reinforcement Learning (RL) …

MERLIN tackles multi-objective task scheduling with hierarchical DRL, outperforming existing methods.

this paper has been withdrawn

Many reinforcement-learning researchers treat the reward function as a part of the environment, meaning that the agent can only know the reward of a state if it encounters that state in a trial run. However, we argue that this is an unnecessary limitation and instead, the reward function should be provided to the learn…

A new multi-objective RL framework improves intrinsic exploration performance.

Study optimality in safety-constrained Markov decision processes using asynchronous value iteration and modified Q-learning.

TAMO optimizes multiple objectives in-context using transformers.

DPA aligns LLMs with multi-objective rewards for diverse user preferences.

The paper proposes a method to infer multi-objective rewards from preferences.

New method tackles parcel routing with AI.

It is notoriously difficult to control the behavior of reinforcement learning agents. Agents often learn to exploit the environment or reward signal and need to be retrained multiple times. The multi-objective reinforcement learning (MORL) framework separates a reward function into several objectives. An ideal MORL age…

This paper analyzes MORL and proposes efficient algorithms to learn Pareto optimal policies.

CARML uses meta-learning to avoid obstacles in 2D vehicle navigation.

Unified framework for multi-objective curriculum learning in robotics.

We present a framework, which we call Molecule Deep $Q$-Networks (MolDQN), for molecule optimization by combining domain knowledge of chemistry and state-of-the-art reinforcement learning techniques (double $Q$-learning and randomized value functions). We directly define modifications on molecules, thereby ensuring 100…

SAMBA improves safe reinforcement learning with active exploration metrics.

The standard reinforcement learning (RL) formulation considers the expectation of the (discounted) cumulative reward. This is limiting in applications where we are concerned with not only the expected performance, but also the distribution of the performance. In this paper, we introduce micro-objective reinforcement le…

Optimizes mobile notifications for multiple objectives using reinforcement learning.

Multi-objective Neural Architecture Search (NAS) aims to discover novel architectures in the presence of multiple conflicting objectives. Despite recent progress, the problem of approximating the full Pareto front accurately and efficiently remains challenging. In this work, we explore the novel reinforcement learning …

Recent studies on neural architecture search have shown that automatically designed neural networks perform as good as expert-crafted architectures. While most existing works aim at finding architectures that optimize the prediction accuracy, these architectures may have complexity and is therefore not suitable being d…

PRISM integrates diverse rewards in MORL, improving sample efficiency and Pareto coverage.

Generative thermal design learns optimal shapes using multi-agent reinforcement learning.

The paper tackles scalarization issues in A2C RL algorithms, proposing methods to avoid gradient overlap and noise.

The most data-efficient algorithms for reinforcement learning in robotics are model-based policy search algorithms, which alternate between learning a dynamical model of the robot and optimizing a policy to maximize the expected return given the model and its uncertainties. However, the current algorithms lack an effec…

Fairness is essential for human society, contributing to stability and productivity. Similarly, fairness is also the key for many multi-agent systems. Taking fairness into multi-agent learning could help multi-agent systems become both efficient and stable. However, learning efficiency and fairness simultaneously is a …

This paper surveys gradient-based multi-objective deep learning methods.

New algorithms for multivariate RL improve decision-making in complex systems.

A new RL framework optimizes drug-like molecules synthetically.

A common approach for defining a reward function for Multi-objective Reinforcement Learning (MORL) problems is the weighted sum of the multiple objectives. The weights are then treated as design parameters dependent on the expertise (and preference) of the person performing the learning, with the typical result that a …

In statistical modelling the biggest threat is concept drift which makes the model gradually showing deteriorating performance over time. There are state of the art methodologies to detect the impact of concept drift, however general strategy considered to overcome the issue in performance is to rebuild or re-calibrate…

This work fills the gap in understanding multi-objective learning generalization.

Novel methods generate diverse policies in reinforcement learning.

This paper introduces multi-objective hyperparameter optimization in machine learning.

A new method for diverse Pareto solutions in multi-objective learning.

Bayesian optimization improves DRL for ESG portfolio management.