Timezone: »

Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making
Nishant Desai · Andrew Critch · Stuart J Russell

Wed Dec 05 02:00 PM -- 04:00 PM (PST) @ Room 517 AB #164

It is commonly believed that an agent making decisions on behalf of two or more principals who have different utility functions should adopt a Pareto optimal policy, i.e. a policy that cannot be improved upon for one principal without making sacrifices for another. Harsanyi's theorem shows that when the principals have a common prior on the outcome distributions of all policies, a Pareto optimal policy for the agent is one that maximizes a fixed, weighted linear combination of the principals’ utilities. In this paper, we derive a more precise generalization for the sequential decision setting in the case of principals with different priors on the dynamics of the environment. We refer to this generalization as the Negotiable Reinforcement Learning (NRL) framework. In this more general case, the relative weight given to each principal’s utility should evolve over time according to how well the agent’s observations conform with that principal’s prior. To gain insight into the dynamics of this new framework, we implement a simple NRL agent and empirically examine its behavior in a simple environment.

Author Information

Nishant Desai (DeepScale)
Andrew Critch (UC Berkeley)
Stuart J Russell (UC Berkeley)

More from the Same Authors