Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation

@inproceedings{Kahn2018ComposableAP,
  title={Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation},
  author={Gregory Kahn and Adam Villaflor and Pieter Abbeel and Sergey Levine},
  booktitle={CoRL},
  year={2018}
}
A general-purpose intelligent robot must be able to learn autonomously and be able to accomplish multiple tasks in order to be deployed in the real world. However, standard reinforcement learning approaches learn separate task-specific policies and assume the reward function for each task is known a priori. We propose a framework that learns event cues from off-policy data, and can flexibly combine these event cues at test time to accomplish different tasks. These event cue labels are not… CONTINUE READING
Tweets
This paper has been referenced on Twitter 43 times. VIEW TWEETS

References

Publications referenced by this paper.
Showing 1-10 of 40 references

End-to-end Driving via Conditional Imitation Learning

  • F. Codevilla, M. Müller, A. López, V. Koltun, A. Dosovitskiy
  • ICRA
  • 2018
1 Excerpt