activity
20172023
most citedR-MADDPG for Partially Observable Environments and Limited Communication

64 citations · 105 across the 36 of their papers we have counts for

collaborators
Showing 2019Show all

18 papers · 1 filter

cs.RO20192 cited

Incremental Learning of Motion Primitives for Pedestrian Trajectory Prediction at Intersections

Golnaz Habibi, Nikita Japuria, Jonathan P. How

This paper presents a novel incremental learning algorithm for pedestrian motion prediction, with the ability to improve the learned model over time when data is incrementally avai…

cs.RO2019

Certified Adversarial Robustness for Deep Reinforcement Learning

Björn Lütjens, Michael Everett, Jonathan P. How

Deep Neural Network-based systems are now the state-of-the-art in many robotics tasks, but their application in safety-critical domains remains dangerous without formal guarantees…

cs.RO2019

Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning

Michael Everett, Yu Fan Chen, Jonathan P. How

Collision avoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning as a framework to m…

eess.SY2019

Dynamic Landing of an Autonomous Quadrotor on a Moving Platform in Turbulent Wind Conditions

Aleix Paris, Brett T. Lopez, Jonathan P. How

Autonomous landing on a moving platform presents unique challenges for multirotor vehicles, including the need to accurately localize the platform, fast trajectory planning, and pr…

cs.AI2019

Robust Opponent Modeling via Adversarial Ensemble Reinforcement Learning in Asymmetric Imperfect-Information Games

Macheng Shen, Jonathan P. How

This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent t…

cs.LG2019

Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning

Arpan Kusari, Jonathan P. How

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 tre…