Related papers: Maximum Entropy Diverse Exploration: Disentangling…

In this paper, we study the optimal dividend problem under the continuous time diffusion model with the bounded dividend rate from the Reinforcement Learning (RL) perspective. Unlike the standard literature, our main focus will be on…

Exploration in high-dimensional, continuous spaces with sparse rewards is an open problem in reinforcement learning. Artificial curiosity algorithms address this by creating rewards that lead to exploration. Given a reinforcement learning…

Integrating expressive generative policies, such as flow-matching models, into offline reinforcement learning (RL) allows agents to capture complex, multi-modal behaviors. While Q-learning with Adjoint Matching (QAM) stabilizes policy…

Inverse Reinforcement Learning (IRL) algorithms infer a reward function that explains demonstrations provided by an expert acting in the environment. Maximum Causal Entropy (MCE) IRL is currently the most popular formulation of IRL, with…

Multi-task IRL allows for the possibility that the expert could be switching between multiple ways of solving the same problem, or interleaving demonstrations of multiple tasks. The learner aims to learn the multiple reward functions that…

Diffusion Policies have become widely used in Imitation Learning, offering several appealing properties, such as generating multimodal and discontinuous behavior. As models are becoming larger to capture more complex capabilities, their…

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…

Reinforcement learning necessitates meticulous reward shaping by specialists to elicit target behaviors, while imitation learning relies on costly task-specific data. In contrast, unsupervised skill discovery can potentially reduce these…

Meta reinforcement learning (Meta-RL) is an approach wherein the experience gained from solving a variety of tasks is distilled into a meta-policy. The meta-policy, when adapted over only a small (or just a single) number of steps, is able…

Value-decomposition methods, which reduce the difficulty of a multi-agent system by decomposing the joint state-action space into local observation-action spaces, have become popular in cooperative multi-agent reinforcement learning (MARL).…

A major challenge in reinforcement learning is exploration, when local dithering methods such as epsilon-greedy sampling are insufficient to solve a given task. Many recent methods have proposed to intrinsically motivate an agent to seek…

Many real-world multiagent learning problems involve safety concerns. In these setups, typical safe reinforcement learning algorithms constrain agents' behavior, limiting exploration -- a crucial component for discovering effective…

This article introduces an imitation learning method for learning maximum entropy policies that comply with constraints demonstrated by expert trajectories executing a task. The formulation of the method takes advantage of results…

Deep ensembles have been shown to extend the positive effect seen in typical ensemble learning to neural networks and to reinforcement learning (RL). However, there is still much to be done to improve the efficiency of such ensemble models.…

In complex reinforcement learning (RL) problems, policies with similar rewards may have substantially different behaviors. It remains a fundamental challenge to optimize rewards while also discovering as many diverse strategies as possible,…

Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution (CTDE), where centralized critics leverage global information to guide decentralized actors. However,…

Many real-world human behaviors can be characterized as a sequential decision making processes, such as urban travelers choices of transport modes and routes (Wu et al. 2017). Differing from choices controlled by machines, which in general…

In Reinforcement Learning (RL), agents aim at maximizing cumulative rewards in a given environment. During the learning process, RL agents face the dilemma of exploitation and exploration: leveraging existing knowledge to acquire rewards or…

Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks by consciously selecting more informative samples to label. Active learning for object detection is more challenging and…

Deep reinforcement learning has achieved impressive success in control tasks. However, its policies, represented as opaque neural networks, are often difficult for humans to understand, verify, and debug, which undermines trust and hinders…