Corpus ID: 42747476

Convergent Actor Critic by Humans

  title={Convergent Actor Critic by Humans},
  author={J. MacGlashan and M. Littman and D. Roberts and R. Loftin and Bei Peng and Matthew E. Taylor},
Programming robot behavior can be painstaking: for a layperson, this path is unavailable without investing significant effort in building up proficiency in coding. In contrast, nearly half of American households have a pet dog and at least some exposure to animal training, suggesting an alternative path for customizing robot behavior. Unfortunately, most existing reinforcement-learning (RL) algorithms are not well suited to learning from human-delivered reinforcement. This paper introduces a… Expand
5 Citations

Figures from this paper

Actor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback
  • 7
  • Highly Influenced
  • PDF
Reinforcement Learning based Embodied Agents Modelling Human Users Through Interaction and Multi-Sensory Perception
  • 3
  • PDF
A Joint Planning and Learning Framework for Human-Aided Decision-Making.
  • Highly Influenced
  • PDF


Reinforcement Learning with Human Teachers: Evidence of Feedback and Guidance with Implications for Learning Performance
  • 235
  • Highly Influential
  • PDF
Training a Robot via Human Feedback: A Case Study
  • 108
  • PDF
Learning behaviors via human-delivered discrete feedback: modeling implicit feedback strategies to speed up learning
  • 67
  • PDF
Dynamic Reward Shaping: Training a Robot by Voice
  • 66
  • PDF
Teaching with Rewards and Punishments: Reinforcement or Communication?
  • 23
  • PDF
Between MDPs and Semi-MDPs: A Framework for Temporal Abstraction in Reinforcement Learning
  • 2,388
  • PDF
Natural actor-critic algorithms
  • 382
  • PDF