2 citations · 2 across the 4 of their papers we have counts for
4 papers
Golden Handcuffs make safer AI agents
Aram Ebtekar, Michael K. Cohen
Reinforcement learners can attain high reward through novel unintended strategies. We study a Bayesian mitigation for general environments: we expand the agent's subjective reward…
RL, but don't do anything I wouldn't do
Michael K. Cohen, Marcus Hutter, Yoshua Bengio +1
In reinforcement learning, if the agent's reward differs from the designers' true utility, even only rarely, the state distribution resulting from the agent's policy can be very ba…
Intelligence and Unambitiousness Using Algorithmic Information Theory
Michael K. Cohen, Badri Vellambi, Marcus Hutter
Algorithmic Information Theory has inspired intractable constructions of general intelligence (AGI), and undiscovered tractable approximations are likely feasible. Reinforcement Le…
Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent
Michael K. Cohen, Elliot Catt, Marcus Hutter
Reinforcement learners are agents that learn to pick actions that lead to high reward. Ideally, the value of a reinforcement learner's policy approaches optimality--where the optim…