Open source
Sparse reward tasks to learn behaviour priors

Sparse reward multi-task domains that require a common set of behaviors to solve. The tasks are setup as 'True/False' predicates which are used to provide reward signal. For instance, going to a target or moving a box to a target can be used to encourage certain behaviors within agents. These tasks have been used with "Behavior Priors for Efficient Reiforcement Learning", "Exploiting Hierarchy for Learning and Transfer in KL-Regularized RL" and "Information asymmetry in KL-regularized RL".

No items found.