Corpus ID: 57189440

Dynamic Planning Networks

@article{Tasfi2018DynamicPN,
  title={Dynamic Planning Networks},
  author={Norman L. Tasfi and Miriam A. M. Capretz},
  journal={ArXiv},
  year={2018},
  volume={abs/1812.11240}
}
We introduce Dynamic Planning Networks (DPN), a novel architecture for deep reinforcement learning, that combines model-based and model-free aspects for online planning. Our architecture learns to dynamically construct plans using a learned state-transition model by selecting and traversing between simulated states and actions to maximize information before acting. In contrast to model-free methods, model-based planning lets the agent efficiently test action hypotheses without performing costly… Expand
2 Citations
The Differentiable Cross-Entropy Method
  • 11
  • PDF
NON-LINEAR REWARDS FOR SUCCESSOR FEATURES
  • 2020

References

SHOWING 1-10 OF 40 REFERENCES
TreeQN and ATreeC: Differentiable Tree Planning for Deep Reinforcement Learning
  • 54
  • Highly Influential
  • PDF
TreeQN and ATreeC: Differentiable Tree-Structured Models for Deep Reinforcement Learning
  • 31
  • Highly Influential
Model-Based Planning with Discrete and Continuous Actions
  • 20
Value Prediction Network
  • 178
  • PDF
Universal Planning Networks
  • 90
  • PDF
Strategic Attentive Writer for Learning Macro-Actions
  • 130
  • PDF
Learning model-based planning from scratch
  • 75
  • PDF
Imagination-Augmented Agents for Deep Reinforcement Learning
  • 321
  • Highly Influential
  • PDF
Dyna, an integrated architecture for learning, planning, and reacting
  • 551
Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics
  • 365
  • PDF
...
1
2
3
4
...