A Benchmark for Cycling Close Pass Near Miss Event Detection from Video Streams

1 code implementation • 24 Apr 2023 • Mingjie Li, Tharindu Rathnayake, Ben Beck, Lingheng Meng, Zijue Chen, Akansel Cosgun, Xiaojun Chang, Dana Kulić

Instance-level detection aims to detect which vehicle in the scene gives rise to a close pass near miss.

Event Detection

Partial Observability during DRL for Robot Control

1 code implementation • 12 Sep 2022 • Lingheng Meng, Rob Gorbet, Dana Kulić

Deep Reinforcement Learning (DRL) has made tremendous advances in both simulated and real-world robot control tasks in recent years.

Memory-based Deep Reinforcement Learning for POMDPs

1 code implementation • 24 Feb 2021 • Lingheng Meng, Rob Gorbet, Dana Kulić

A promising characteristic of Deep Reinforcement Learning (DRL) is its capability to learn optimal policy in an end-to-end manner without relying on feature engineering.

Feature Engineering reinforcement-learning +1

The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning

no code implementations • 23 Jun 2020 • Lingheng Meng, Rob Gorbet, Dana Kulić

Recently, research in Deep Reinforcement Learning (DRL) also shows that multi-step methods improve learning speed and final performance in applications where the value-function and policy are represented with deep neural networks.

reinforcement-learning Reinforcement Learning (RL)