Getting Started

Literature Review:

• "Using Geometric Features to Represent Near-Contact Behavior in Robotic Grasping"
• "Learning Near-Contact Grasping Strategies with DeepRL"

General Resources:

DDPG

• Medium: https://towardsdatascience.com/deep-deterministic-policy-gradients-explained-2d94655a9b7b

This article breaks down the network setup and equations discussed in "Continuous Control With Deep Reinforcement Learning"

• Research: https://arxiv.org/abs/1509.02971

Reinforcement Learning (RL)

Learning in continuous action spaces:

• "Using Deep Reinforcement Learning for the Continuous Control of Robotic Arms": https://arxiv.org/pdf/1810.06746.pdf

Key terms/concepts:

• Basic overview of RL: https://towardsdatascience.com/reinforcement-learning-101-e24b50e1d292
• Key terms: https://spinningup.openai.com/en/latest/spinningup/rl_intro.html