D2RL: Deep Dense Architectures in Reinforcement Learning
While improvements in deep learning architectures have played a crucial role in improving the state of supervised and unsupervised learning in computer vision and natural language processing, neural network architecture choices for reinforcement learning remain relatively under-explored. We take inspiration from successful architectural choices in computer vision and generative modelling, and investigate the use of deeper networks and dense connections for reinforcement learning on a variety of simulated robotic learning benchmark environments. Our findings reveal that current methods benefit significantly from dense connections and deeper networks, across a suite of manipulation and locomotion tasks, for both proprioceptive and image-based observations. We hope that our results can serve as a strong baseline and further motivate future research into neural network architectures for reinforcement learning. The project website with code is at this link https://sites.google.com/view/d2rl/home.
Code (4)
Tasks
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Quasimetric Value Functions with Dense Rewards
As a generalization of reinforcement learning (RL) to parametrizable goals, goal conditioned RL (GCRL) has a broad range of applications, particularly in challenging tasks in robotics. Recent work has established that th…
continuous-controlContinuous ControlReinforcement Learning (RL)Learning to Search Efficient DenseNet with Layer-wise Pruning
Deep neural networks have achieved outstanding performance in many real-world applications with the expense of huge computational resources. The DenseNet, one of the recently proposed neural network architecture, has ach…
Reinforcement LearningEvolving Character-Level DenseNet Architectures using Genetic Programming
DenseNet architectures have demonstrated impressive performance in image classification tasks, but limited research has been conducted on using character-level DenseNet (char-DenseNet) architectures for text classificati…
ClassificationGeneral Classificationimage-classificationImage Classification+2Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning
Scaling neural networks has driven breakthrough advances in machine learning, yet this paradigm fails in deep reinforcement learning (DRL), where larger models often degrade performance due to unique optimization patholo…
Reinforcement LearningCRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies
Open-loop imitation learning has advanced modern autonomous driving policy architectures, but closed-loop deployment remains vulnerable to policy-induced distribution shift. Existing post-training paradigms exhibit funda…
Autonomous Driving