Pith. sign in

REVIEW 4 cited by

D2RL: Deep Dense Architectures in Reinforcement Learning

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2010.09163 v2 pith:YHVEEFEM submitted 2020-10-19 cs.LG

Samarth Sinha , Homanga Bharadhwaj , Aravind Srinivas , Animesh Garg This is my paper · ORCID
classification cs.LG
keywords learningreinforcementarchitecturesdensechoicescomputerconnectionsd2rl
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DextrAH-RGB: Visuomotor Policies to Grasp Anything with Dexterous Hands

    cs.RO 2024-11 conditional novelty 7.0 of 10

    A dexterous robot hand learns to grasp novel objects from color images alone, trained purely in simulation, and demonstrates competitive real-world performance versus depth-camera policies.

  2. Online Training and Pruning of Deep Reinforcement Learning Networks

    cs.LG 2025-07 conditional novelty 6.0 of 10

    A method that prunes OFENet-based reinforcement learning networks during training, reducing them to a fraction of their original size with minimal performance loss.

  3. A Forget-and-Grow Strategy for Deep Reinforcement Learning Scaling in Continuous Control

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Forget and Grow (FoG) combines decaying replay weights for old experiences with progressive critic-network expansion to improve continuous-control reinforcement learning, beating BRO, SimBa, and TD-MPC2 on most of 41 ...

  4. M2I2HA: Multi-modal Object Detection Based on Intra- and Inter-Modal Hypergraph Attention

    cs.CV 2026-01 conditional novelty 4.0 of 10

    M2I2HA adds intra-modal and cross-modal hypergraph attention modules to a YOLO-style detector and reports the best average precision on DroneVehicle and FLIR, while on LLVIP and VEDAI prior methods score higher on the...

Pith tools