Reinforcement Learning Models of Emotion : Computational Challenges

@inproceedings{Broekens2017ReinforcementLM,
  title={Reinforcement Learning Models of Emotion : Computational Challenges},
  author={Joost Broekens},
  year={2017}
}
In this paper we address the field that computationally studies the relation between adaptive behavior and emotion. This field studies how affective phenomena emerge from simulated adaptive agents and how these agents and their human interaction partners can benefit from this. In particular, we focus on four major challenges when adaptive behavior is operationalized as an agent that learns to solve a task using reinforcement learning (RL) and affect is a signal that is derived from RL… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 72 REFERENCES

Socio-Emotional Reward Design for Intrinsically Motivated Learning Agents

Pedro Sequeira
  • Ph.D. dissertation, Inesc-ID Lisbon,
  • 2013
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Meta-learning in Reinforcement Learning

  • Neural Networks
  • 2003
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Jonker , ‘ A reinforcement learning model of joy , distress , hope and fear

Joost Broekens, Elmer Jacobs, M Catholijn
  • 2015

Similar Papers

Loading similar papers…