Corpus ID: 14273320

PILCO: A Model-Based and Data-Efficient Approach to Policy Search

@inproceedings{Deisenroth2011PILCOAM,
  title={PILCO: A Model-Based and Data-Efficient Approach to Policy Search},
  author={M. Deisenroth and C. Rasmussen},
  booktitle={ICML},
  year={2011}
}
In this paper, we introduce PILCO, a practical, data-efficient model-based policy search method. [...] Key Method Policy evaluation is performed in closed form using state-of-the-art approximate inference. Furthermore, policy gradients are computed analytically for policy improvement. We report unprecedented learning efficiency on challenging and high-dimensional control tasks.Expand

Figures, Tables, and Topics from this paper

Model-Based Reinforcement Learning via Proximal Policy Optimization
Uncertainty-aware Model-based Policy Optimization
SAMBA: Safe Model-Based & Active Reinforcement Learning
Data-Efficient Reinforcement Learning in Continuous State-Action Gaussian-POMDPs
Learning Off-Policy with Online Planning
Regularizing Model-Based Planning with Energy-Based Models
Hierarchical model-based policy optimization: from actions to action sequences and back
Minimax Model Learning
Exploring Model-based Planning with Policy Networks
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 39 REFERENCES
Using inaccurate models in reinforcement learning
Model-free off-policy reinforcement learning in continuous environment
  • P. Wawrzynski, A. Pacut
  • Computer Science
  • 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)
  • 2004
Incorporating Domain Models into Bayesian Optimization for RL
Efficient reinforcement learning using Gaussian processes
Exploiting Model Uncertainty Estimates for Safe Dynamic Control Learning
Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning
Reinforcement Learning in Continuous Time and Space
  • K. Doya
  • Mathematics, Medicine
  • Neural Computation
  • 2000
Policy Gradient Methods for Robotics
  • Jan Peters, S. Schaal
  • Engineering, Computer Science
  • 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems
  • 2006
...
1
2
3
4
...