Fractional Transfer Learning for Deep Model-Based Reinforcement Learning
arXiv:2108.06526
Abstract
Reinforcement learning (RL) is well known for requiring large amounts of data in order for RL agents to learn to perform complex tasks. Recent progress in model-based RL allows agents to be much more data-efficient, as it enables them to learn behaviors of visual environments in imagination by leveraging an internal World Model of the environment. Improved sample efficiency can also be achieved by reusing knowledge from previously learned tasks, but transfer learning is still a challenging topic in RL. Parameter-based transfer learning is generally done using an all-or-nothing approach, where the network's parameters are either fully transferred or randomly initialized. In this work we present a simple alternative approach: fractional transfer learning. The idea is to transfer fractions of knowledge, opposed to discarding potentially useful knowledge as is commonly done with random initialization. Using the World Model-based Dreamer algorithm, we identify which type of components this approach is applicable to, and perform experiments in a new multi-source transfer learning setting. The results show that fractional transfer learning often leads to substantially improved performance and faster learning compared to learning from scratch and random initialization.
arXiv comment21 pages, 8 figures, 7 tables
References in corpus (17)
- Auto-Encoding Variational Bayes
- Distilling the Knowledge in a Neural Network
- Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
- Dota 2 with Large Scale Deep Reinforcement Learning
- Model-Based Reinforcement Learning for Atari
- Learning Latent Dynamics for Planning from Pixels
- Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images
- Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
- Distral: Robust Multitask Reinforcement Learning
- Transfer Learning in Deep Reinforcement Learning: A Survey
- Dream to Control: Learning Behaviors by Latent Imagination
- Decoupling Dynamics and Reward for Transfer Learning
- Importance Weighted Transfer of Samples in Reinforcement Learning
- Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
- Smooth Exploration for Robotic Reinforcement Learning
- Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings
- A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning