Low Dimensional State Representation Learning with Robotics Priors in Continuous Action Spaces

by   Nicolò Botteghi, et al.

Autonomous robots require high degrees of cognitive and motoric intelligence to come into our everyday life. In non-structured environments and in the presence of uncertainties, such degrees of intelligence are not easy to obtain. Reinforcement learning algorithms have proven to be capable of solving complicated robotics tasks in an end-to-end fashion without any need for hand-crafted features or policies. Especially in the context of robotics, in which the cost of real-world data is usually extremely high, reinforcement learning solutions achieving high sample efficiency are needed. In this paper, we propose a framework combining the learning of a low-dimensional state representation, from high-dimensional observations coming from the robot's raw sensory readings, with the learning of the optimal policy, given the learned state representation. We evaluate our framework in the context of mobile robot navigation in the case of continuous state and action spaces. Moreover, we study the problem of transferring what learned in the simulated virtual environment to the real robot without further retraining using real-world data in the presence of visual and depth distractors, such as lighting changes and moving obstacles.


page 1

page 5

page 6


Low Dimensional State Representation Learning with Reward-shaped Priors

Reinforcement Learning has been able to solve many complicated robotics ...

On the Geometry of Reinforcement Learning in Continuous State and Action Spaces

Advances in reinforcement learning have led to its successful applicatio...

Learning to Actively Reduce Memory Requirements for Robot Control Tasks

Robots equipped with rich sensing modalities (e.g., RGB-D cameras) perfo...

Learning Real-World Robot Policies by Dreaming

Learning to control robots directly based on images is a primary challen...

Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics

Scaling end-to-end reinforcement learning to control real robots from vi...

Sim2Real for Peg-Hole Insertion with Eye-in-Hand Camera

Even though the peg-hole insertion is one of the well-studied problems i...

Unsupervised state representation learning with robotic priors: a robustness benchmark

Our understanding of the world depends highly on our capacity to produce...

Please sign up or login with your details

Forgot password? Click here to reset