Related papers: Sub-policy Adaptation for Hierarchical Reinforceme…
Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on…
Advancing the dynamic loco-manipulation capabilities of quadruped robots in complex terrains is crucial for performing diverse tasks. Specifically, dynamic ball manipulation in rugged environments presents two key challenges. The first is…
Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a group receive the same reward, the group yields zero relative…
Proximal Policy Optimization (PPO) is among the most widely used deep reinforcement learning algorithms, yet its theoretical foundations remain incomplete. Most importantly, convergence and understanding of fundamental PPO advantages remain…
We present HiDe, a novel hierarchical reinforcement learning architecture that successfully solves long horizon control tasks and generalizes to unseen test scenarios. Functional decomposition between planning and low-level control is…
For many applications of reinforcement learning it can be more convenient to specify both a reward function and constraints, rather than trying to design behavior through the reward function. For example, systems that physically interact…
Learning an optimal policy from a multi-modal reward function is a challenging problem in reinforcement learning (RL). Hierarchical RL (HRL) tackles this problem by learning a hierarchical policy, where multiple option policies are in…
Constrained Reinforcement Learning (RL) aims to maximize the return while adhering to predefined constraint limits, which represent domain-specific safety requirements. In continuous control settings, where learning agents govern system…
Aligning large language models (LLMs) on domain-specific data remains a fundamental challenge. Supervised fine-tuning (SFT) offers a straightforward way to inject domain knowledge but often degrades the model's generality. In contrast,…
Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal…
In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…
Reinforcement learning practitioners often avoid hierarchical policies, especially in image-based observation spaces. Typically, the single-task performance improvement over flat-policy counterparts does not justify the additional…
Hierarchical reinforcement learning (HRL) improves the efficiency of long-horizon reinforcement-learning tasks with sparse rewards by decomposing the task into a hierarchy of subgoals. The main challenge of HRL is efficient discovery of the…
Recent advances in multi-agent reinforcement learning (MARL) have created opportunities to solve complex real-world tasks. Cybersecurity is a notable application area, where defending networks against sophisticated adversaries remains a…
This paper presents a hierarchical reinforcement learning (RL) approach to address the agent grouping or pairing problem in cooperative multi-agent systems. The goal is to simultaneously learn the optimal grouping and agent policy. By…
Proximal Policy Optimization with Adaptive Exploration (axPPO) is introduced as a novel learning algorithm. This paper investigates the exploration-exploitation tradeoff within the context of reinforcement learning and aims to contribute…
Long-horizon manipulation tasks such as stacking represent a longstanding challenge in the field of robotic manipulation, particularly when using reinforcement learning (RL) methods which often struggle to learn the correct sequence of…
Models with fewer parameters are necessary for the neural control of memory-limited, performant robots. Finding these smaller neural network architectures can be time-consuming. We propose HyperPPO, an on-policy reinforcement learning…
Direct Preference Optimization (DPO) is an effective framework for aligning large language models with human preferences, but it struggles with complex reasoning tasks. DPO optimizes for the likelihood of generating preferred over…
Deep reinforcement learning (DRL) has emerged as a powerful framework for solving sequential decision-making problems, achieving remarkable success in a wide range of applications, including game AI, autonomous driving, biomedicine, and…