MicroRacer: A Didactic Environment for Deep Reinforcement Learning

Asperti, Andrea; Brutto, Marco Del

doi:10.1007/978-3-031-25599-1_18

Cited by 2 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to discretization methods for managing motion actions, DRL approaches like the DDPG learn policies directly without explicit discretization. However, the DDPG poses challenges in validation and reproducibility for continuous actions, varying implementations leading to inconsistent performance and generalization [34], catastrophic forgetting resulting in large fluctuations in training [35]. A3C [34], employing asynchronous gradient descent with concurrent environment instances, enhances training stability through parallel agents, while A2C [34], its synchronous counterpart, balances exploration-exploitation with a focus on uncertain value estimate states, often measured using entropy, and both demonstrate comparable performance in various scenarios.…”

Section: State Actor-critic Methodsmentioning

confidence: 99%

Improving the Performance of Autonomous Driving through Deep Reinforcement Learning

Tammewar,

Chaudhari,

Saini

et al. 2023

Sustainability

View full text Add to dashboard Cite

Reinforcement learning (RL) is revolutionizing the artificial intelligence (AI) domain and significantly aiding in building autonomous systems with a higher level comprehension of the world as we observe it. Deep learning (DL) facilitates RL to scale and resolve previously intractable problems, for instance, allowing supervision principles designed for robots to be acquired directly from visual data, developing video game proficiency from pixel-level information, etc. Recent research shows that RL algorithms help represent problems dealing with high-dimensional, unprocessed data input and can have successful applications in computer vision, pattern identification, natural language analysis, and speech parsing. This research paper focuses on training a simulation model of a car to navigate autonomously on a racetrack using RL. The study explores several fundamental algorithms in Deep RL, namely Proximal Policy Optimization (PPO), Deep Q-network (DQN), and Deep Deterministic Policy Gradient (DDPG). The paper documents a comparative analysis of these three prominent algorithms—based on their speed, accuracy, and overall performance. After a thorough evaluation, the research indicates that the DQN surpassed the other existing algorithms. This study further examined the performance of the DQN with and without ε-decay and observed that the DQN with ε-decay is better suited for our objective and is significantly more stable than its non ε-decay counterpart. The findings from this research could assist in improving the performance and stability of autonomous vehicles using the DQN with ε -decay. It concludes by discussing the fine-tuning of the model for future real-world applications and the potential research areas within the field of autonomous driving.

show abstract

Section: State Actor-critic Methodsmentioning

confidence: 99%

Improving the Performance of Autonomous Driving through Deep Reinforcement Learning

Tammewar,

Chaudhari,

Saini

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…Diffusion probabilistic models are outperforming existing state-of-the-art methods in various fields and applications [10,11]. Recent advancements in image-to-image translation tasks, such as inpainting and colorization, have showcased the potential of diffusion models to achieve superior performance compared to other state-of-the-art generative architectures.…”

Section: State Of the Artmentioning

confidence: 99%

Low-Cost Training of Image-to-Image Diffusion Models with Incremental Learning and Task/Domain Adaptation

Antona,

Otero,

Tous

2024

Electronics

View full text Add to dashboard Cite

Diffusion models specialized in image-to-image translation tasks, like inpainting and colorization, have outperformed the state of the art, yet their computational requirements are exceptionally demanding. This study analyzes different strategies to train image-to-image diffusion models in a low-resource setting. The studied strategies include incremental learning and task/domain transfer learning. First, a base model for human face inpainting is trained from scratch with an incremental learning strategy. The resulting model achieves an FID score almost equivalent to that of its batch learning equivalent while significantly reducing the training time. Second, the base model is fine-tuned to perform a different task, image colorization, and, in a different domain, landscape images. The resulting colorization models showcase exceptional performances with a minimal number of training epochs. We examine the impact of different configurations and provide insights into the ability of image-to-image diffusion models for transfer learning across tasks and domains.

show abstract

MicroRacer: A Didactic Environment for Deep Reinforcement Learning

Cited by 2 publications

References 17 publications

Improving the Performance of Autonomous Driving through Deep Reinforcement Learning

Improving the Performance of Autonomous Driving through Deep Reinforcement Learning

Low-Cost Training of Image-to-Image Diffusion Models with Incremental Learning and Task/Domain Adaptation

Contact Info

Product

Resources

About