Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction
@inproceedings{Sutton2011HordeAS, title={Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction}, author={R. Sutton and Joseph Modayil and M. Delp and T. Degris and P. Pilarski and Adam White and Doina Precup}, booktitle={AAMAS}, year={2011} }
Maintaining accurate world knowledge in a complex and changing environment is a perennial problem for robots and other artificial intelligence systems. Our architecture for addressing this problem, called Horde, consists of a large number of independent reinforcement learning sub-agents, or demons. Each demon is responsible for answering a single predictive or goal-oriented question about the world, thereby contributing in a factored, modular way to the system's overall knowledge. The questions… CONTINUE READING
321 Citations
Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation
- Computer Science, Engineering
- CoRL
- 2018
- 9
- Highly Influenced
- PDF
BECCA: Reintegrating AI for Natural World Interaction
- Computer Science
- AAAI Spring Symposium: Designing Intelligent Robots
- 2012
- 12
Self-organizing maps for storage and transfer of knowledge in reinforcement learning
- Computer Science
- Adapt. Behav.
- 2019
- 10
- PDF
Accelerating Learning in Constructive Predictive Frameworks with the Successor Representation
- Computer Science, Mathematics
- 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- 2018
- 5
- PDF
Meta-learning for Predictive Knowledge Architectures: A Case Study Using TIDBD on a Sensor-rich Robotic Arm
- Computer Science
- AAMAS
- 2019
- 1
- PDF
References
SHOWING 1-10 OF 28 REFERENCES
Map Learning with Uninterpreted Sensors and Effectors
- Mathematics, Computer Science
- Artif. Intell.
- 1997
- 217
- PDF
Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning
- Computer Science
- Artif. Intell.
- 1999
- 2,340
- PDF
A Method for Clustering the Experiences of a Mobile Robot that Accords with Human Judgments
- Computer Science
- AAAI/IAAI
- 2000
- 96
- PDF
Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming
- Computer Science
- ML
- 1990
- 1,432
- PDF
Linking Action to Perception in a Humanoid Robot: a Developmental Approach to Grasping
- Computer Science
- 2004
- 46
- PDF
Reinforcement Learning: An Introduction
- Computer Science
- IEEE Transactions on Neural Networks
- 2005
- 27,059
- PDF
Neo: learning conceptual knowledge by sensorimotor interaction with an environment
- Computer Science
- AGENTS '97
- 1997
- 49
- PDF