mlsanityData to 7 Oct 2026

MBDP: A Model-based Approach to Achieve both Robustness and Sample Efficiency via Double Dropout Planning

arXiv 2108.01295 ↗First posted 3 Aug 2021cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Model-based reinforcement learning is a widely accepted solution for solving excessive sample demands. However, the predictions of the dynamics models are often not accurate enough, and the resulting bias may incur catastrophic decisions due to insufficient robustness. Therefore, it is highly desired to investigate how to improve the robustness of model-based RL algorithms while maintaining high sampling efficiency. In this paper, we propose Model-Based Double-dropout Planning (MBDP) to balance robustness and efficiency. MBDP consists of two kinds of dropout mechanisms, where the rollout-dropout aims to improve the robustness with a small cost of sample efficiency, while the model-dropout is designed to compensate for the lost efficiency at a slight expense of robustness. By combining them in a complementary way, MBDP provides a flexible control mechanism to meet different demands of robustness and efficiency by tuning two corresponding dropout ratios. The effectiveness of MBDP is demonstrated both theoretically and experimentally.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 32 references that are in the map. First posted on arXiv 3 Aug 2021.

Builds on

17 of 32 references.

References · 17

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 1,916
  4. 2015End-to-End Training of Deep Visuomotor Policiescited by 847
  5. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 753
  6. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  7. 2017Robust Adversarial Reinforcement Learningcited by 439
  8. 2017Safe Model-based Reinforcement Learning with Stability Guaranteescited by 347
  9. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 214
  10. 2018Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansioncited by 167
  11. 2019Action Robust Reinforcement Learning and Applications in Continuous Controlcited by 167
  12. 2015Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approachcited by 162
5 more
  1. 2018Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guaranteescited by 138
  2. 2016EPOpt: Learning Robust Neural Network Policies Using Model Ensemblescited by 136
  3. 2014Optimizing the CVaR via Samplingcited by 98
  4. 2019Combating the Compounding-Error Problem with a Multi-step Modelcited by 52
  5. 2019Calibrated Model-Based Deep Reinforcement Learningcited by 31

Built on by

Not cited yet.