Timezone: »

 
Poster
A Composable Specification Language for Reinforcement Learning Tasks
Kishor Jothimurugan · Rajeev Alur · Osbert Bastani

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #221
in Reinforcement Learning and Planning -- Reinforcement Learning »

Reinforcement learning is a promising approach for learning control policies for robot tasks. However, specifying complex tasks (e.g., with multiple objectives and safety constraints) can be challenging, since the user must design a reward function that encodes the entire task. Furthermore, the user often needs to manually shape the reward to ensure convergence of the learning algorithm. We propose a language for specifying complex control tasks, along with an algorithm that compiles specifications in our language into a reward function and automatically performs reward shaping. We implement our approach in a tool called SPECTRL, and show that it outperforms several state-of-the-art baselines.

Keywords: Reinforcement Learning and Planning · Planning · Reinforcement Learning and Planning
[ Paper]  [ Slides] 

Author Information

Kishor Jothimurugan (University of Pennsylvania)
Rajeev Alur (University of Pennsylvania)
Osbert Bastani (University of Pennysylvania)

More from the Same Authors