On The Transferability Of Deep-q Networks

Abstract

Transfer Learning (TL) is an efficient machine learning paradigm that allows overcoming some of the hurdles that characterize the successful training of deep neural networks, ranging from long training times to the needs of large datasets. While exploiting TL is a well established and successful training practice in Supervised Learning (SL), its applicability in Deep Reinforcement Learning (DRL) is rarer. In this paper, we study the level of transferability of three different variants of Deep-Q Networks on popular DRL benchmarks as well as on a set of novel, carefully designed control tasks. Our results show that transferring neural networks in a DRL context can be particularly challenging and is a process which in most cases results in negative transfer. In the attempt of understanding why Deep-Q Networks transfer so poorly, we gain novel insights into the training dynamics that characterizes this family of algorithms.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysabatelli2021on

Related papers

• How Transferable Are The Representations Learned By Deep Q Agents? (2020)0.00
• Deep Transfer \(q\)-learning For Offline Non-stationary Reinforcement Learning (2025)0.00
• SF-DQN: Provable Knowledge Transfer Using Successor Feature For Deep Reinforcement Learning (2024)0.00
• Target Transfer Q-learning And Its Convergence Analysis (2018)0.00
• Transfer Q-learning (2022)0.00
• Automaton Distillation: Neuro-symbolic Transfer Learning For Deep Reinforcement Learning (2023)0.00
• Transfer Learning In Deep Reinforcement Learning: A Survey (2020)20.93
• Deep Q-networks For Accelerating The Training Of Deep Neural Networks (2016)0.00