Information Theoretically Aided Reinforcement Learning for Embodied Agents
@article{Montfar2016InformationTA, title={Information Theoretically Aided Reinforcement Learning for Embodied Agents}, author={Guido Mont{\'u}far and K. Zahedi and N. Ay}, journal={ArXiv}, year={2016}, volume={abs/1605.09735} }
Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental setting, that incorporating an intrinsic reward can smoothen the optimization landscape while preserving the global optimizers of interest. We show that policy gradient optimization for locomotion in a complex morphology is significantly improved when… CONTINUE READING
Figures and Topics from this paper
8 Citations
A Unified Bellman Optimality Principle Combining Reward Maximization and Empowerment
- Computer Science, Mathematics
- NeurIPS
- 2019
- 6
- PDF
Curiosity-Driven Reinforcement Learning with Homeostatic Regulation
- Computer Science
- 2018 International Joint Conference on Neural Networks (IJCNN)
- 2018
- 16
- PDF
A unified strategy for implementing curiosity and empowerment driven reinforcement learning
- Computer Science
- ArXiv
- 2018
- 8
- PDF
References
SHOWING 1-10 OF 24 REFERENCES
Curiosity driven reinforcement learning for motion planning on humanoids
- Computer Science, Medicine
- Front. Neurorobot.
- 2014
- 59
- PDF
Learning and exploration in action-perception loops
- Computer Science, Medicine
- Front. Neural Circuits
- 2013
- 76
- PDF
Linear combination of one-step predictive information with an external reward in an episodic policy gradient setting: a critical analysis
- Computer Science, Medicine
- Front. Psychol.
- 2013
- 10
- PDF
An information-theoretic approach to curiosity-driven reinforcement learning
- Computer Science, Medicine
- Theory in Biosciences
- 2011
- 126
- PDF
Reinforcement Learning: An Introduction
- Computer Science
- IEEE Transactions on Neural Networks
- 2005
- 27,047
- PDF
Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
- Computer Science, Mathematics
- NIPS
- 2015
- 223
- PDF
Intrinsically Motivated Learning in Natural and Artificial Systems
- Computer Science, Psychology
- 2013
- 204
Higher Coordination With Less Control—A Result of Information Maximization in the Sensorimotor Loop
- Computer Science, Mathematics
- Adapt. Behav.
- 2010
- 65
- PDF