mlsanityData to 14 Oct 2026

One is More: Diverse Perspectives within a Single Network for Efficient DRL

arXiv 2310.14009 ↗First posted 21 Oct 2023cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep reinforcement learning has achieved remarkable performance in various domains by leveraging deep neural networks for approximating value functions and policies. However, using neural networks to approximate value functions or policy functions still faces challenges, including low sample efficiency and overfitting. In this paper, we introduce OMNet, a novel learning paradigm utilizing multiple subnetworks within a single network, offering diverse outputs efficiently. We provide a systematic pipeline, including initialization, training, and sampling with OMNet. OMNet can be easily applied to various deep reinforcement learning algorithms with minimal additional overhead. Through comprehensive evaluations conducted on MuJoCo benchmark, our findings highlight OMNet's ability to strike an effective balance between performance and computational cost.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 21 Oct 2023.

Builds on

43 of 56 references.

References · 43

  1. 2016Layer Normalizationcited by 5,669
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  3. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  4. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,262
  5. 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
  6. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  7. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  8. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  9. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 676
  10. 2019Linear Mode Connectivity and the Lottery Ticket Hypothesiscited by 637
  11. 2020MOPO: Model-based Offline Policy Optimizationcited by 636
  12. 2017To prune, or not to prune: exploring the efficacy of pruning for model compressioncited by 603
31 more
  1. 2019Rigging the Lottery: Making All Tickets Winnerscited by 495
  2. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 471
  3. 2017Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Sciencecited by 328
  4. 2021Randomized Ensembled Double Q-Learning: Learning Fast Without a Modelcited by 288
  5. 2022The Primacy Bias in Deep Reinforcement Learningcited by 247
  6. 2021Mastering Atari Games with Limited Datacited by 237
  7. 2017Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeoncited by 221
  8. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 219
  9. 2020Proving the Lottery Ticket Hypothesis: Pruning is All You Needcited by 201
  10. 2023The Dormant Neuron Phenomenon in Deep Reinforcement Learningcited by 174
  11. 2023Understanding plasticity in neural networkscited by 174
  12. 2021A Survey of Zero-shot Generalisation in Deep Reinforcement Learningcited by 170
  13. 2018Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansioncited by 168
  14. 2020SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learningcited by 152
  15. 2021Robust Reinforcement Learning on State Observations with Learned Optimal Adversarycited by 135
  16. 2018Assessing Generalization in Deep Reinforcement Learningcited by 133
  17. 2022Understanding and Preventing Capacity Loss in Reinforcement Learningcited by 125
  18. 2021Dropout Q-Functions for Doubly Efficient Reinforcement Learningcited by 114
  19. 2016Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learningcited by 106
  20. 2020Transient Non-Stationarity and Generalisation in Deep Reinforcement Learningcited by 75
  21. 2017Towards Generalization and Simplicity in Continuous Controlcited by 68
  22. 2022The State of Sparse Training in Deep Reinforcement Learningcited by 61
  23. 2021Dynamic Sparse Training for Deep Reinforcement Learningcited by 49
  24. 2023Efficient Deep Reinforcement Learning Requires Regulating Overfittingcited by 36
  25. 2022RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratchcited by 30
  26. 2022Training Your Sparse Neural Network Better with Any Maskcited by 26
  27. 2021Single-Shot Pruning for Offline Reinforcement Learningcited by 21
  28. 2022Towards Applicable Reinforcement Learning: Improving the Generalization and Sample Efficiency with Policy Ensemblecited by 18
  29. 2023Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selectioncited by 14
  30. 2018ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Searchcited by 12
  31. 2019The Search for Sparse, Robust Neural Networkscited by 11

Built on by

Not cited yet.