Human-Inspired Framework to Accelerate Reinforcement Learning

2023-02-28 · Ali Beikmohammadi, Sindri Magnússon

Reinforcement learning (RL) is crucial for data science decision-making but suffers from sample inefficiency, particularly in real-world scenarios with costly physical interactions. This paper introduces a novel human-inspired framework to enhance RL algorithm sample efficiency. It achieves this by initially exposing the learning agent to simpler tasks that progressively increase in complexity, ultimately leading to the main task. This method requires no pre-training and involves learning simpler tasks for just one iteration. The resulting knowledge can facilitate various transfer learning approaches, such as value and policy transfer, without increasing computational complexity. It can be applied across different goals, environments, and RL algorithms, including value-based, policy-based, tabular, and deep RL methods. Experimental evaluations demonstrate the framework's effectiveness in enhancing sample efficiency, especially in challenging main tasks, demonstrated through both a simple Random Walk and more complex optimal control problems with constraints.

📄 PDF Abstract BibTeX arXiv:2303.08115

Code (1)

AliBeikmohammadi/TA-Explore 공식 구현 tf

Tasks

Decision Making reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Transfer Learning

Towards Brain-inspired System: Deep Recurrent Reinforcement Learning for Simulated Self-driving Agent

2019-03-29 · Jieneng Chen, Jingye Chen, Ruiming Zhang, Xiaobin Hu

An effective way to achieve intelligence is to simulate various intelligent behaviors in the human brain. In recent years, bio-inspired learning methods have emerged, and they are different from the classical mathematica…

Decision Making OpenAI Gym reinforcement-learning Reinforcement Learning+1

DIPPER: Direct Preference Optimization to Accelerate Primitive-Enabled Hierarchical Reinforcement Learning

2024-06-16 · Utsav Singh, Souradip Chakraborty, Wesley A. Suttle, Brian M. Sadler 외

Learning control policies to perform complex robotics tasks from human preference data presents significant challenges. On the one hand, the complexity of such tasks typically requires learning policies to perform a vari…

Computational Efficiency Hierarchical Reinforcement Learning reinforcement-learning Reinforcement Learning

Active Learning for Risk-Sensitive Inverse Reinforcement Learning

2019-09-14 · Rui Chen, Wenshuo Wang, Zirui Zhao, Ding Zhao

One typical assumption in inverse reinforcement learning (IRL) is that human experts act to optimize the expected utility of a stochastic cost with a fixed distribution. This assumption deviates from actual human behavio…

Active Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Swimming Under Constraints: A Safe Reinforcement Learning Framework for Quadrupedal Bio-Inspired Propulsion

2026-03-04 · Xinyu Cui, Fei Han, Hang Xu, Yongcheng Zeng 외 arxiv

Bio-inspired aquatic propulsion offers high thrust and maneuverability but is prone to destabilizing forces such as lift fluctuations, which are further amplified by six-degree-of-freedom (6-DoF) fluid coupling. We formu…

Reinforcement Learning

Accelerated Target Updates for Q-learning

2019-05-07 · Bowen Weng, Huaqing Xiong, Wei zhang

This paper studies accelerations in Q-learning algorithms. We propose an accelerated target update scheme by incorporating the historical iterates of Q functions. The idea is conceptually inspired by the momentum-based a…

Atari Games Q-Learning reinforcement-learning Reinforcement Learning+1