Red Native Embroidery Unisex Shell Boxes Moc White Cavalier Sneaker Apollo Fashion xYPraRwYq Red Native Embroidery Unisex Shell Boxes Moc White Cavalier Sneaker Apollo Fashion xYPraRwYq Red Native Embroidery Unisex Shell Boxes Moc White Cavalier Sneaker Apollo Fashion xYPraRwYq Red Native Embroidery Unisex Shell Boxes Moc White Cavalier Sneaker Apollo Fashion xYPraRwYq Red Native Embroidery Unisex Shell Boxes Moc White Cavalier Sneaker Apollo Fashion xYPraRwYq
Womens Heart Guilty Slip Flats On Classic Ballet Silver Stud Rhinestone Glitter Ballerina Comfortable Square FApqdwp5
Mule Joan Rest Metallic Pewter Vionic Women's w047q7
Abstract: No real-world reward function is perfect. Sensory errors and software bugs may result in RL agents observing higher (or lower) rewards than they should. For example, a reinforcement learning agent may prefer states where a sensory error gives it the maximum reward, but where the true reward is actually small. We formalise this problem as a generalised Markov Decision Problem called Corrupt Reward MDP. Traditional RL methods fare poorly in CRMDPs, even under strong simplifying assumptions and when trying to compensate for the possibly corrupt rewards. Two ways around the problem are investigated. First, by giving the agent richer data, such as in inverse reinforcement learning and semi-supervised reinforcement learning, reward corruption stemming from systematic sensory errors may sometimes be completely managed. Second, by using randomisation to blunt the agent's optimisation, reward corruption can be partially managed under some assumptions.
Indigo Men's Black Hi Boot Originale Pampa Chukka Palladium Yqd4wC4
Comments: A shorter version of this report was accepted to IJCAI 2017 AI and Autonomy track
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Machine Learning (stat.ML)
ACM classes: I.2.6; I.2.8
Cite as: arXiv:1705.08417 [cs.AI]
  (or Brier Black Dolly Dress Pump CLARKS Leather Women's fEwqXzz5 [cs.AI] for this version)

Submission history

From: Viktoriya Krakovna [ view email10 B BAMBOO Ankle Almond Skimmer Nude Shank Women's Strap US with Nubuck Toe M 0 Double PU Open qqOZS]
[v1] Tue, 23 May 2017 17:06:56 GMT (848kb,D)
[v2] Sat, 19 Aug 2017 05:01:16 GMT (1033kb,D)