paper-with-me

Papers

D2RL: Deep Dense Architectures in Reinforcement Learning

2020-10-19 · Samarth Sinha, Homanga Bharadhwaj, Aravind Srinivas, Animesh Garg

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.

📄 PDF Abstract BibTeX arXiv:2010.09163

Code (4)

pairlab/d2rl 공식 구현 pytorch
BY571/Soft-Actor-Critic-and-Extensions pytorch
ku2482/rljax jax
mugoh/rl-base/tree/master/rlbase/d2rl pytorch

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Quasimetric Value Functions with Dense Rewards

2024-09-13 · Khadichabonu Valieva, Bikramjit Banerjee

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

2019-05-01 · ICLR 2019 5 · Xuanyang Zhang, Hao liu, Zhanxing Zhu, Zenglin Xu

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 Learning

Evolving Character-Level DenseNet Architectures using Genetic Programming

2020-12-03 · Trevor Londt, Xiaoying Gao, Peter Andreae

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+2

Rethinking the Role of Dynamic Sparse Training for Scalable Deep Reinforcement Learning

2025-10-14 · Guozheng Ma, Lu Li, Zilin Wang, Haoyu Wang 외 arxiv

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 Learning

CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies

2026-05-06 · Keyu Chen, Nanfei Ye, Yida Wang, Wenchao Sun 외 arxiv

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