• Computer Science, Mathematics
  • Published in NeurIPS 2019

Real-Time Reinforcement Learning

@inproceedings{Ramstedt2019RealTimeRL,
  title={Real-Time Reinforcement Learning},
  author={Simon Ramstedt and Chris Pal},
  booktitle={NeurIPS},
  year={2019}
}
Markov Decision Processes (MDPs), the mathematical framework underlying most algorithms in Reinforcement Learning (RL), are often used in a way that wrongfully assumes that the state of an agent's environment does not change during action selection. As RL systems based on MDPs begin to find application in real-world safety critical situations, this mismatch between the assumptions underlying classical MDPs and the reality of real-time computation may lead to undesirable outcomes. In this paper… CONTINUE READING

Figures, Tables, and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 21 REFERENCES

Soft Actor-Critic Algorithms and Applications

VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Humanlevel control through deep reinforcement learning

  • Mnih, Volodymyr, +17 authors Georg
  • Advances in neural information processing systems
  • 2015
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

Learning agile and dynamic motor skills for legged robots

VIEW 2 EXCERPTS

Control of a quadrotor with reinforcement learning

  • Hwangbo, Jemin, +5 authors Marco
  • IEEE Robotics and Automation Letters,
  • 2017
VIEW 2 EXCERPTS

Mastering the game of Go without human knowledge

VIEW 2 EXCERPTS