Preference elicitation and inverse reinforcement learning

@inproceedings{Rothkopf2011PreferenceEA,
  title={Preference elicitation and inverse reinforcement learning},
  author={C. Rothkopf and Christos Dimitrakakis},
  booktitle={ECML/PKDD},
  year={2011}
}
We state the problem of inverse reinforcement learning in terms of preference elicitation, resulting in a principled (Bayesian) statistical formulation. This generalises previous work on Bayesian inverse reinforcement learning and allows us to obtain a posterior distribution on the agent's preferences, policy and optionally, the obtained reward sequence, from observations. We examine the relation of the resulting approach to other statistical methods for inverse reinforcement learning via… Expand
64 Citations
A Policy Iteration Algorithm for Learning from Preference-Based Feedback
  • 7
Hierarchical Bayesian Inverse Reinforcement Learning
  • 13
  • PDF
Probabilistic inverse reinforcement learning in unknown environments
  • 10
  • PDF
A Survey of Preference-Based Reinforcement Learning Methods
  • 89
  • PDF
Bayesian Multitask Inverse Reinforcement Learning
  • 79
  • PDF
Robust Bayesian Reinforcement Learning through Tight Lower Bounds
  • 13
  • PDF
Inverse Reinforcement Learning with Simultaneous Estimation of Rewards and Dynamics
  • 41
  • PDF
Reinforcement Learning in Economics and Finance
  • 6
  • PDF
Guiding Autonomous Agents to Better Behaviors through Human Advice
  • 29
  • PDF
Towards Resolving Unidentifiability in Inverse Reinforcement Learning
  • 16
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 27 REFERENCES
Bayesian Inverse Reinforcement Learning
  • 503
  • PDF
Bayesian Multitask Inverse Reinforcement Learning
  • 79
  • PDF
A POMDP formulation of preference elicitation problems
  • 271
  • PDF
Apprenticeship learning via inverse reinforcement learning
  • 2,136
  • PDF
Variational methods for Reinforcement Learning
  • 46
  • PDF
A Game-Theoretic Approach to Apprenticeship Learning
  • 226
  • PDF
Gaussian Process Preference Elicitation
  • 75
  • PDF
A Reduction from Apprenticeship Learning to Classification
  • 52
  • PDF
...
1
2
3
...