Papers › Collision Avoidance Robotics Via Meta-Learning (CARML)

Collision Avoidance Robotics Via Meta-Learning (CARML)

16 Jul 2020arXiv:2007.08616archive 2025-07-28

Abhiram Iyer, Aravind Mahadevan

This paper presents an approach to exploring a multi-objective reinforcement learning problem with Model-Agnostic Meta-Learning. The environment we used consists of a 2D vehicle equipped with a LIDAR sensor. The goal of the environment is to reach some pre-determined target location but also effectively avoid any obstacles it may find along its path. We also compare this approach against a baseline TD3 solution that attempts to solve the same problem.

Paper PDF Code

Code

abhi-iyer/meta-learning officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Collision Avoidance Meta-Learning Multi-Objective Reinforcement Learning Reinforcement Learning Reinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Clipped Double Q-learning Dense Connections Experience Replay ReLU TD3 Target Policy Smoothing

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections