RealAnt: An Open-Source Low-Cost Quadruped for Research in Real-World Reinforcement Learning

Current robot platforms available for research are either very expensive or unable to handle the abuse of exploratory controls in reinforcement learning. We develop RealAnt, a minimal low-cost physical version of the popular 'Ant' benchmark used in reinforcement learning... (read more)

PDF Abstract

Tasks


Datasets


  Add Datasets introduced or used in this paper

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper


METHOD TYPE
Experience Replay
Replay Memory
Adam
Stochastic Optimization
Clipped Double Q-learning
Off-Policy TD Control
ReLU
Activation Functions
Target Policy Smoothing
Regularization
Dense Connections
Feedforward Networks
TD3
Policy Gradient Methods