Timezone: »

Delayed Reinforcement Learning by Imitation
Pierre Liotet · Davide Maran · Lorenzo Bisi · Marcello Restelli

Wed Jul 20 02:40 PM -- 02:45 PM (PDT) @ Hall G

When the agent's observations or interactions are delayed, classic reinforcement learning tools usually fail. In this paper, we propose a simple yet new and efficient solution to this problem. We assume that, in the undelayed environment, an efficient policy is known or can be easily learnt, but the task may suffer from delays in practice and we thus want to take them into account. We present a novel algorithm, Delayed Imitation with Dataset Aggregation (DIDA), which builds upon imitation learning methods to learn how to act in a delayed environment from undelayed demonstrations. We provide a theoretical analysis of the approach that will guide the practical design of DIDA. These results are also of general interest in the delayed reinforcement learning literature by providing bounds on the performance between delayed and undelayed tasks, under smoothness conditions. We show empirically that DIDA obtains high performances with a remarkable sample efficiency on a variety of tasks, including robotic locomotion, classic control, and trading.

Author Information

Pierre Liotet (Politecnico di Milano)

Currently a Ph.D. student at Politecnico di Milano. My research interests include reinforcement learning in environments with partial observability, delays and the lifelong reinforcement learning setting.

Davide Maran (Politecnico di Milano)
Lorenzo Bisi (Politecnico di Milano)
Marcello Restelli (Politecnico di Milano)

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

More from the Same Authors