38 citations · 95 across the 8 of their papers we have counts for
12 papers
Adversarial Motion Priors Make Good Substitutes for Complex Reward Functions
Alejandro Escontrela, Xue Bin Peng, Wenhao Yu +4
Training a high-dimensional simulated agent with an under-specified reward function often leads the agent to learn physically infeasible strategies that are ineffective when deploy…
Disentangled Planning and Control in Vision Based Robotics via Reward Machines
Alberto Camacho, Jacob Varley, Deepali Jain +2
In this work we augment a Deep Q-Learning agent with a Reward Machine (DQRM) to increase speed of learning vision-based policies for robot tasks, and overcome some of the limitatio…
From Pixels to Legs: Hierarchical Learning of Quadruped Locomotion
Deepali Jain, Atil Iscen, Ken Caluwaerts
Legged robots navigating crowded scenes and complex terrains in the real world are required to execute dynamic leg movements while processing visual input for obstacle avoidance an…
Learning Agile Locomotion Skills with a Mentor
Atil Iscen, George Yu, Alejandro Escontrela +3
Developing agile behaviors for legged robots remains a challenging problem. While deep reinforcement learning is a promising approach, learning truly agile behaviors typically requ…
Zero-Shot Terrain Generalization for Visual Locomotion Policies
Alejandro Escontrela, George Yu, Peng Xu +2
Legged robots have unparalleled mobility on unstructured terrains. However, it remains an open challenge to design locomotion controllers that can operate in a large variety of env…
Policies Modulating Trajectory Generators
Atil Iscen, Ken Caluwaerts, Jie Tan +4
We propose an architecture for learning complex controllable behaviors by having simple Policies Modulate Trajectory Generators (PMTG), a powerful combination that can provide both…