Related papers: DD-PPO: Learning Near-Perfect PointGoal Navigators…

Policy optimization methods with function approximation are widely used in multi-agent reinforcement learning. However, it remains elusive how to design such algorithms with statistical guarantees. Leveraging a multi-agent performance…

Training reinforcement learning (RL) policies for legged robots remains challenging due to high-dimensional continuous actions, hardware constraints, and limited exploration. Existing methods for locomotion and whole-body control work well…

Direct Preference Optimization (DPO) simplifies reinforcement learning from human feedback (RLHF) for large language models (LLMs) by directly optimizing human preferences without an explicit reward model. We find that during DPO training,…

Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually considered despite its…

In this paper, we propose two novel decentralized optimization frameworks for multi-agent nonlinear optimal control problems in robotics. The aim of this work is to suggest architectures that inherit the computational efficiency and…

A central challenge for autonomous vehicles is coordinating with humans. Therefore, incorporating realistic human agents is essential for scalable training and evaluation of autonomous driving systems in simulation. Simulation agents are…

Parameter updating is an important stage in parallelism-based distributed deep learning. Synchronous methods are widely used in distributed training the Deep Neural Networks (DNNs). To reduce the communication and synchronization overhead…

We present Habitat, a platform for research in embodied artificial intelligence (AI). Habitat enables training embodied agents (virtual robots) in highly efficient photorealistic 3D simulation. Specifically, Habitat consists of: (i)…

Interpretation of Deep Neural Networks (DNNs) training as an optimal control problem with nonlinear dynamical systems has received considerable attention recently, yet the algorithmic development remains relatively limited. In this work, we…

At the forefront of state-of-the-art human alignment methods are preference optimization methods (*PO). Prior research has often concentrated on identifying the best-performing method, typically involving a grid search over hyperparameters,…

The Unrelated Parallel Machine Scheduling Problem (UPMSP) with release dates, setups, and eligibility constraints presents a significant multi-objective challenge. Traditional methods struggle to balance minimizing Total Weighted Tardiness…

Distributed pose graph optimization (DPGO) is one of the fundamental techniques of swarm robotics. Currently, the sub-problems of DPGO are built on the native poses. Our validation proves that this approach may introduce an imbalance in the…

Autonomous exploration of obstacle-rich spaces requires strategies that ensure efficiency while guaranteeing safety against collisions with obstacles. This paper investigates a novel platform-agnostic reinforcement learning framework that…

Deep reinforcement learning (DRL) is one of the promising approaches for introducing robots into complicated environments. The recent remarkable progress of DRL stands on regularization of policy, which allows the policy to improve stably…

Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic…

Large-scale AI model training divides work across thousands of GPUs, then synchronizes gradients across them at each step. This incurs a significant network burden that only centralized, monolithic clusters can support, driving up…

Predictive power allocation is conceived for energy-efficient video streaming over mobile networks using deep reinforcement learning. The goal is to minimize the accumulated energy consumption of each base station over a complete video…

Recent advancements in reinforcement learning from human feedback have shown that utilizing fine-grained token-level reward models can substantially enhance the performance of Proximal Policy Optimization (PPO) in aligning large language…

This paper introduces HEPPO-GAE, an FPGA-based accelerator designed to optimize the Generalized Advantage Estimation (GAE) stage in Proximal Policy Optimization (PPO). Unlike previous approaches that focused on trajectory collection and…

Novel advanced policy gradient (APG) methods, such as Trust Region policy optimization and Proximal policy optimization (PPO), have become the dominant reinforcement learning algorithms because of their ease of implementation and good…