Curriculum-based Asymmetric Multi-task Reinforcement Learning

2022-11-07 · Hanchi Huang, Deheng Ye, Li Shen, Wei Liu

We introduce CAMRL, the first curriculum-based asymmetric multi-task learning (AMTL) algorithm for dealing with multiple reinforcement learning (RL) tasks altogether. To mitigate the negative influence of customizing the one-off training order in curriculum-based AMTL, CAMRL switches its training mode between parallel single-task RL and asymmetric multi-task RL (MTRL), according to an indicator regarding the training time, the overall performance, and the performance gap among tasks. To leverage the multi-sourced prior knowledge flexibly and to reduce negative transfer in AMTL, we customize a composite loss with multiple differentiable ranking functions and optimize the loss through alternating optimization and the Frank-Wolfe algorithm. The uncertainty-based automatic adjustment of hyper-parameters is also applied to eliminate the need of laborious hyper-parameter analysis during optimization. By optimizing the composite loss, CAMRL predicts the next training task and continuously revisits the transfer matrix and network weights. We have conducted experiments on a wide range of benchmarks in multi-task RL, covering Gym-minigrid, Meta-world, Atari video games, vision-based PyBullet tasks, and RLBench, to show the improvements of CAMRL over the corresponding single-task RL algorithm and state-of-the-art MTRL algorithms. The code is available at: https://github.com/huanghanchi/CAMRL

📄 PDF Abstract BibTeX arXiv:2211.03352

Code (1)

huanghanchi/camrl 공식 구현 pytorch

Tasks

Multi-Task Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

AC-MASAC: An Attentive Curriculum Learning Framework for Heterogeneous UAV Swarm Coordination

2026-02-12 · Wanhao Liu, Junhong Dai, Yixuan Zhang, Shengyun Yin 외 arxiv

Cooperative path planning for heterogeneous UAV swarms poses significant challenges for Multi-Agent Reinforcement Learning (MARL), particularly in handling asymmetric inter-agent dependencies and addressing the risks of …

Multi-agent Reinforcement Learning

It Takes Four to Tango: Multiagent Selfplay for Automatic Curriculum Generation

2022-02-22 · Yuqing Du, Pieter Abbeel, Aditya Grover

We are interested in training general-purpose reinforcement learning agents that can solve a wide variety of goals. Training such agents efficiently requires automatic generation of a goal curriculum. This is challenging…

It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation

2021-09-29 · ICLR 2022 4 · Yuqing Du, Pieter Abbeel, Aditya Grover

We are interested in training general-purpose reinforcement learning agents that can solve a wide variety of goals. Training such agents without excessive interactions requires automatic generation of a goal curriculum.…

Deep Reinforcement Learning for Multi-Agent Coordination

2025-10-04 · Kehinde O. Aina, Sehoon Ha arxiv

We address the challenge of coordinating multiple robots in narrow and confined environments, where congestion and interference often hinder collective task performance. Drawing inspiration from insect colonies, which ac…

Reinforcement Learning

Learning Curriculum Policies for Reinforcement Learning

2018-12-01 · Sanmit Narvekar, Peter Stone

Curriculum learning in reinforcement learning is a training methodology that seeks to speed up learning of a difficult target task, by first training on a series of simpler tasks and transferring the knowledge acquired t…

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