Transfer Learning and Curriculum Learning in Sokoban
arXiv:2105.11702
Abstract
Transfer learning can speed up training in machine learning and is regularly used in classification tasks. It reuses prior knowledge from other tasks to pre-train networks for new tasks. In reinforcement learning, learning actions for a behavior policy that can be applied to new environments is still a challenge, especially for tasks that involve much planning. Sokoban is a challenging puzzle game. It has been used widely as a benchmark in planning-based reinforcement learning. In this paper, we show how prior knowledge improves learning in Sokoban tasks. We find that reusing feature representations learned previously can accelerate learning new, more complex, instances. In effect, we show how curriculum learning, from simple to complex tasks, works in Sokoban. Furthermore, feature representations learned in simpler instances are more general, and thus lead to positive transfers towards more complex tasks, but not vice versa. We have also studied which part of the knowledge is most important for transfer to succeed, and identify which layers should be used for pre-training.
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- How transferable are features in deep neural networks?
- Language Models are Few-Shot Learners
- Agent57: Outperforming the Atari Human Benchmark
- Imagination-Augmented Agents for Deep Reinforcement Learning
- On the role of planning in model-based deep reinforcement learning
- Sample-Efficient Reinforcement Learning through Transfer and Architectural Priors
- A Novel Automated Curriculum Strategy to Solve Hard Sokoban Planning Instances
- Solving Hard AI Planning Instances Using Curriculum-Driven Deep Reinforcement Learning