Visual Tracking by means of Deep Reinforcement Learning and an Expert Demonstrator

2019-09-18 · Matteo Dunnhofer, Niki Martinel, Gian Luca Foresti, Christian Micheloni

In the last decade many different algorithms have been proposed to track a generic object in videos. Their execution on recent large-scale video datasets can produce a great amount of various tracking behaviours. New trends in Reinforcement Learning showed that demonstrations of an expert agent can be efficiently used to speed-up the process of policy learning. Taking inspiration from such works and from the recent applications of Reinforcement Learning to visual tracking, we propose two novel trackers, A3CT, which exploits demonstrations of a state-of-the-art tracker to learn an effective tracking policy, and A3CTD, that takes advantage of the same expert tracker to correct its behaviour during tracking. Through an extensive experimental validation on the GOT-10k, OTB-100, LaSOT, UAV123 and VOT benchmarks, we show that the proposed trackers achieve state-of-the-art performance while running in real-time.

📄 PDF Abstract BibTeX arXiv:1909.08487

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement Learningreinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Visual Tracking

Action Guidance with MCTS for Deep Reinforcement Learning

2019-07-25 · Bilal Kartal, Pablo Hernandez-Leal, Matthew E. Taylor

Deep reinforcement learning has achieved great successes in recent years, however, one main challenge is the sample inefficiency. In this paper, we focus on how to use action guidance by means of a non-expert demonstrato…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Safer Deep RL with Shallow MCTS: A Case Study in Pommerman

2019-04-10 · Bilal Kartal, Pablo Hernandez-Leal, Chao GAO, Matthew E. Taylor

Safe reinforcement learning has many variants and it is still an open research problem. Here, we focus on how to use action guidance by means of a non-expert demonstrator to avoid catastrophic events in a domain with spa…

Deep Reinforcement Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Inverse Reinforcement Learning by Estimating Expertise of Demonstrators

2024-02-02 · Mark Beliaev, Ramtin Pedarsani

In Imitation Learning (IL), utilizing suboptimal and heterogeneous demonstrations presents a substantial challenge due to the varied nature of real-world data. However, standard IL algorithms consider these datasets as h…

Imitation Learning reinforcement-learning Reinforcement Learning

Modelling, Positioning, and Deep Reinforcement Learning Path Tracking Control of Scaled Robotic Vehicles: Design and Experimental Validation

2024-01-10 · Carmine Caponio, Pietro Stano, Raffaele Carli, Ignazio Olivieri 외

Mobile robotic systems are becoming increasingly popular. These systems are used in various indoor applications, raging from warehousing and manufacturing to test benches for assessment of advanced control strategies, su…

Deep Reinforcement Learning State Estimation

Avoidance Learning Using Observational Reinforcement Learning

2019-09-24 · David Venuto, Leonard Boussioux, Junhao Wang, Rola Dali 외

Imitation learning seeks to learn an expert policy from sampled demonstrations. However, in the real world, it is often difficult to find a perfect expert and avoiding dangerous behaviors becomes relevant for safety reas…

Imitation Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)