# Articles

#### Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control

Abstract Deep reinforcement learning has demonstrated increasing capabilities for continuous control problems, including agents that can move with skill and agility through their environment. An open problem in this setting is that of developing good strategies for integrating or merging policies for multiple skills, where each individual skill is a …

#### Demistifying the Many Deep Reinforcement Learning Algorithms

Intro In recient years there has been an explosion in Deep Reinforcement learning research resulting in the creation of many different RL algorithms that work with deep networks. In DeepRL and RL in general the goal is to train a policy $$\pi(a|s,\theta)$$ with parameters $$\theta$$. It is …

#### Deep Rienforcement Learning: A course on the subject

Reinforcemen learning is large and accelerating area of research. The recent advances in combining RL method with Deep learning have given way to solutions to challenging problems Like playing Atari and Robotic Manipulation. These advances have been wonderful but as many practitioners might have relized getting these methods to work …

#### KL Divergence Regularization for RL

Intro Regularization is a very common practice in machine learning. In supervized learning it is used to reduce model complexity. It also helps prevent the model from over fitting the test data. In RL because of the availablility of limitless data regularization does not need to be used to reduce …

#### DeepLoco: Dynamic Locomotion Skills Using Hierarchical Deep Reinforcement Learning

Abstract Learning physics-based locomotion skills is a difficult problem, leading to solutions that typically exploit prior knowledge of various forms. In this paper we aim to learn a variety of environment-aware locomotion skills with a limited amount of prior knowledge. We adopt a two-level hierarchical control framework. First, low-level controllers …