Posts
LTL$_f$ Reactive Synthesis under Environment Specifications
Reactive synthesis can be viewed as a game between the $environment$ and the $agent$, where the agent tries to achieve its task with respect to environment m...
Generalized Planning as Heuristic Search
Heuristic search is one of the most successful approaches to classical planning. Unfortunately, it is not straightforward to adopt state-of-the-art search a...
Learning Sketches for Decomposing Planning Problems into Subproblems of Bounded Width
In reinforcement learning (RL), the intrinsic reward function defines reward signals that help learning policies in cases where the extrinsic rewards are spa...
Metrics for Evaluating Generalized Plans
The computation and analysis of representations that aid generalizability and transfer in planning is a rich area of research with multiple approaches. For ...
Submit an article!
To submit an article, please contact the blog moderator, Pulkit Verma at pulkitv@mit.edu and follow the process below.