Modeling the world can benefit robot learning by providing a rich training signal for shaping an agent's latent state space. However, learning world models in unconstrained environments over high-dimensional observation spaces such as images is challenging. One source of difficulty is the presence of irrelevant but hard-to-model background distractions, and unimportant visual details of task-relevant entities. We address this issue by learning a recurrent latent dynamics model which contrastively predicts the next observation. This simple model leads to surprisingly robust robotic control even with simultaneous camera, background, and color distractions. We outperform alternatives such as bisimulation methods which impose state-similarity measures derived from divergence in future reward or future optimal actions. We obtain state-of-the-art results on the Distracting Control Suite, a challenging benchmark for pixel-based robotic control.

Related readings and updates.

ARtonomous: Introducing Middle School Students to Reinforcement Learning Through Virtual Robotics

Typical educational robotics approaches rely on imperative programming for robot navigation. However, with the increasing presence of AI in everyday life, these approaches miss an opportunity to introduce machine learning (ML) techniques grounded in an authentic and engaging learning context. Furthermore, the needs for costly specialized equipment and ample physical space are barriers that limit access to robotics experiences for all learners. We…
See paper details

Learning Conditional Error Model for Simulated Time-Series Data

Applications such as autonomous navigation [1], human-robot interaction [2], game-playing robots [8], etc., use simulation to minimize the cost of testing in real world. Furthermore, some machine learning algorithms, like reinforcement learning, use simulation for training a model. To test reliably in simulation or deploy a model in the real world that is trained with simulated data, the simulator should be representative of the real environment…
See paper details