Fine-tuning deep RL with gradient-free optimization

Deep reinforcement learning makes it possible to train control policies that map high-dimensional observations to actions. These methods typically use gradient-based optimization techniques to enable relatively efficient learning, but are notoriously sensitive to hyperparameter choices and do not have good convergence properties. Gradient...

Integrating state representation learning into deep reinforcement learning

Most deep reinforcement learning techniques are unsuitable for robotics, as they require too much interaction time to learn useful, general control policies. This problem can be largely attributed to the fact that a state representation needs to be learned as a part of learning control policies, which can only be done through fitting expected...

Experience selection in deep reinforcement learning for control

Experience replay is a technique that allows off-policy reinforcement-learning methods to reuse past experiences. The stability and speed of convergence of reinforcement learning, as well as the eventual performance of the learned policy, are strongly dependent on the experiences being replayed. Which experiences are replayed depends on two...

Efficient Optical Flow and Stereo Vision for Velocity Estimation and Obstacle Avoidance on an Autonomous Pocket Drone

Micro Aerial Vehicles (FOV) are very suitable for flying in indoor environments, but autonomous navigation is challenging due to their strict hardware limitations. This paper presents a highly efficient computer vision algorithm called Edge-FS for the determination of velocity and depth. It runs at 20 Hz on a 4 g stereo camera with an embedded...

Local histogram matching for efficient optical flow computation applied to velocity estimation on pocket drones

Autonomous flight of pocket drones is challenging due to the severe limitations on on-board energy, sensing, and processing power. However, tiny drones have great potential as their small size allows maneuvering through narrow spaces while their small weight provides significant safety advantages. This paper presents a computationally efficient...

Improved deep reinforcement learning for robotics through distribution-based experience retention

Recent years have seen a growing interest in the use of deep neural networks as function approximators in reinforcement learning. In this paper, an experience replay method is proposed that ensures that the distribution of the experiences used for training is between that of the policy and a uniform distribution. Through experiments on a...