Related papers: RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control

RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control

URL: http://arxiv.org/abs/2210.11262v1
Date: Thu, 20 Oct 2022 13:34:26 GMT
Title: RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control
Authors: Yanfei Xiang, Xin Wang, Shu Hu, Bin Zhu, Xiaomeng Huang, Xi Wu, Siwei Lyu
Abstract summary: Reinforcement learning is applied to solve actual complex tasks from high-dimensional, sensory inputs. Recent progress benefits from deep learning for raw sensory signal representation. We present RMBench, the first benchmark for robotic manipulations.
Score: 47.61691569074207
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Reinforcement learning is applied to solve actual complex tasks from high-dimensional, sensory inputs. The last decade has developed a long list of reinforcement learning algorithms. Recent progress benefits from deep learning for raw sensory signal representation. One question naturally arises: how well do they perform concerning different robotic manipulation tasks? Benchmarks use objective performance metrics to offer a scientific way to compare algorithms. In this paper, we present RMBench, the first benchmark for robotic manipulations, which have high-dimensional continuous action and state spaces. We implement and evaluate reinforcement learning algorithms that directly use observed pixels as inputs. We report their average performance and learning curves to show their performance and stability of training. Our study concludes that none of the studied algorithms can handle all tasks well, soft Actor-Critic outperforms most algorithms in average reward and stability, and an algorithm combined with data augmentation may facilitate learning policies. Our code is publicly available at https://anonymous.4open.science/r/RMBench-2022-3424, including all benchmark tasks and studied algorithms.

Related papers

Reinforcement Learning with Action Sequence for Data-Efficient Robot Learning [62.3886343725955]
We introduce a novel RL algorithm that learns a critic network that outputs Q-values over a sequence of actions. By explicitly training the value functions to learn the consequence of executing a series of current and future actions, our algorithm allows for learning useful value functions from noisy trajectories.
arXiv Detail & Related papers (2024-11-19T01:23:52Z)
A Comparison of Imitation Learning Algorithms for Bimanual Manipulation [22.531439806919547]
In this work, we demonstrate the limitations and benefits of prominent imitation learning approaches. We evaluate each algorithm on a complex bimanual manipulation task involving an over-constrained dynamics system. We find that imitation learning is well suited to solve such complex tasks, but not all algorithms are equal in terms of handling perturbations, training requirements, performance, and ease of use.
arXiv Detail & Related papers (2024-08-13T00:04:17Z)
Offline Imitation Learning Through Graph Search and Retrieval [57.57306578140857]
Imitation learning is a powerful machine learning algorithm for a robot to acquire manipulation skills. We propose GSR, a simple yet effective algorithm that learns from suboptimal demonstrations through Graph Search and Retrieval. GSR can achieve a 10% to 30% higher success rate and over 30% higher proficiency compared to baselines.
arXiv Detail & Related papers (2024-07-22T06:12:21Z)
A Generalist Neural Algorithmic Learner [18.425083543441776]
We build a single graph neural network processor capable of learning to execute a wide range of algorithms. We show that it is possible to effectively learn algorithms in a multi-task manner, so long as we can learn to execute them well in a single-task regime.
arXiv Detail & Related papers (2022-09-22T16:41:33Z)
The CLRS Algorithmic Reasoning Benchmark [28.789225199559834]
Learning representations of algorithms is an emerging area of machine learning, seeking to bridge concepts from neural networks with classical algorithms. We propose the CLRS Algorithmic Reasoning Benchmark, covering classical algorithms from the Introduction to Algorithms textbook. Our benchmark spans a variety of algorithmic reasoning procedures, including sorting, searching, dynamic programming, graph algorithms, string algorithms and geometric algorithms.
arXiv Detail & Related papers (2022-05-31T09:56:44Z)
Benchmarking Processor Performance by Multi-Threaded Machine Learning Algorithms [0.0]
In this paper, I will make a performance comparison of multi-threaded machine learning clustering algorithms. I will be working on Linear Regression, Random Forest, and K-Nearest Neighbors to determine the performance characteristics of the algorithms.
arXiv Detail & Related papers (2021-09-11T13:26:58Z)
Evolving Reinforcement Learning Algorithms [186.62294652057062]
We propose a method for meta-learning reinforcement learning algorithms. The learned algorithms are domain-agnostic and can generalize to new environments not seen during training. We highlight two learned algorithms which obtain good generalization performance over other classical control tasks, gridworld type tasks, and Atari games.
arXiv Detail & Related papers (2021-01-08T18:55:07Z)
A Framework for Efficient Robotic Manipulation [79.10407063260473]
We show that a single robotic arm can learn sparse-reward manipulation policies from pixels. We show that, given only 10 demonstrations, a single robotic arm can learn sparse-reward manipulation policies from pixels.
arXiv Detail & Related papers (2020-12-14T22:18:39Z)
Mastering Rate based Curriculum Learning [78.45222238426246]
We argue that the notion of learning progress itself has several shortcomings that lead to a low sample efficiency for the learner. We propose a new algorithm, based on the notion of mastering rate, that significantly outperforms learning progress-based algorithms.
arXiv Detail & Related papers (2020-08-14T16:34:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.