Alexandre Galashov

TL;DR: This work proposes a method that separately learns the policy and the task belief by taking advantage of various kinds of privileged information, which can be very effective at solving standard meta-RL environments, as well as a complex continuous control environment with sparse rewards and requiring long-term memory.

TL;DR: This work proposes a framework specific for the scenario where no information about task boundaries or task identity is given, and proposes a separation of concerns into what task is being solved and how the task should be solved, which opens the door to combining meta-learning and continual learning techniques, leveraging their complementary advantages.

TL;DR: A motor architecture that has the general structure of an inverse model with a latent-variable bottleneck is proposed, and it is shown that it is possible to train this model entirely offline to compress thousands of expert policies and learn a motor primitive embedding space.

TL;DR: This work starts from the KL regularized expected reward objective and introduces an additional component, a default policy, but crucially restricts the amount of information the default policy receives, forcing it to learn reusable behaviors that help the policy learn faster.

TL;DR: In this paper, the authors propose a motor architecture that has the general structure of an inverse model with a latent-variable bottleneck, and show that it is possible to train this model entirely offline to compress thousands of expert policies.