pith. sign in

arxiv: 2111.11156 · v2 · pith:DQHT3RWF · submitted 2021-11-22 · cs.RO

Improved Reinforcement Learning Pushing Policies via Heuristic Rules

pith:DQHT3RWFopen to challenge →

classification cs.RO
keywords heuristicruletargetdemonstrateimprovedlearningobjectorder
0
0 comments X
read the original abstract

Non-prehensile pushing actions have the potential to singulate a target object from its surrounding clutter in order to facilitate the robotic grasping of the target. To address this problem we utilize a heuristic rule that moves the target object towards the workspace's empty space and demonstrate that this simple heuristic rule achieves singulation. We incorporate this effective heuristic rule to the reward in order to train more efficiently reinforcement learning (RL) agents for singulation. Simulation experiments demonstrate that this insight increases performance. Finally, our results show that the RL-based policy implicitly learns something similar to one of the used heuristics in terms of decision making. Qualitative results, code, pre-trained models and simulation environments are available at https://github.com/robot-clutter/improved_rl.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.