Corpus ID: 676516

Efficient Exploration in Reinforcement Learning Based on Short-term Memory

@inproceedings{Pchelkin2002EfficientEI,
  title={Efficient Exploration in Reinforcement Learning Based on Short-term Memory},
  author={A. Pchelkin},
  year={2002}
}
Reinforcement learning addresses the question of how an autonomous agent that senses and acts in its environment can learn to choose optimal actions to achieve its goals. It is related to the problem of learning control strategies. In practice multiple situations are usually indistinguishable from immediate perceptual input. These multiple situations may require different responses from the agent. So, there is a need to use short-term memory to solve this incomplete perception problem… Expand

Figures from this paper

References

SHOWING 1-10 OF 12 REFERENCES
Efficient Exploration in Reinforcement Learning with Hidden State
  • 20
  • Highly Influential
Efficient Exploration In Reinforcement Learning
  • 221
  • Highly Influential
The role of exploration in learning control
  • 230
  • Highly Influential
Reinforcement Learning: An Introduction
  • 28,064
  • PDF
Reinforcement Learning: A Survey
  • 6,738
  • PDF
Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming
  • 1,453
  • PDF
Complexity and Cooperation in Q-Learning
  • 90
Modeling adaptive autonomous agents
  • 448
Knowledge Growth in an Artificial Animal
  • 343
Learning probabilistic automata with variable memory length
  • 116
  • PDF
...
1
2
...