Timezone: »

Offline Reinforcement Learning with Pseudometric Learning
Robert Dadashi · Shideh Rezaeifar · Nino Vieillard · Léonard Hussenot · Olivier Pietquin · Matthieu Geist

Tue Jul 20 07:30 AM -- 07:35 AM (PDT) @ None

Offline Reinforcement Learning methods seek to learn a policy from logged transitions of an environment, without any interaction. In the presence of function approximation, and under the assumption of limited coverage of the state-action space of the environment, it is necessary to enforce the policy to visit state-action pairs close to the support of logged transitions. In this work, we propose an iterative procedure to learn a pseudometric (closely related to bisimulation metrics) from logged transitions, and use it to define this notion of closeness. We show its convergence and extend it to the function approximation setting. We then use this pseudometric to define a new lookup based bonus in an actor-critic algorithm: PLOFF. This bonus encourages the actor to stay close, in terms of the defined pseudometric, to the support of logged transitions. Finally, we evaluate the method on hand manipulation and locomotion tasks.

Author Information

Robert Dadashi (Google Research)
Shideh Rezaeifar (University of Geneva)
Nino Vieillard (Google Brain)
Léonard Hussenot (Google Research, Brain Team)
Olivier Pietquin (GOOGLE BRAIN)
Matthieu Geist (Google)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors