Learning Time-Sensitive Strategies in Space Fortress
arXiv:1805.06824
Abstract
Although there has been remarkable progress and impressive performance on reinforcement learning (RL) on Atari games, there are many problems with challenging characteristics that have not yet been explored in Deep Learning for RL. These include reward sparsity, abrupt context-dependent reversals of strategy and time-sensitive game play. In this paper, we present Space Fortress, a game that incorporates all these characteristics and experimentally show that the presence of any of these renders state of the art Deep RL algorithms incapable of learning. Then, we present our enhancements to an existing algorithm and show big performance increases through each enhancement through an ablation study. We discuss how each of these enhancements was able to help and also argue that appropriate transfer learning boosts performance.
arXiv comment10 pages, 3 figures. Withdrawn, superseded by arXiv:1809.02206
References in corpus (6)
- Sequence to Sequence Learning with Neural Networks
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Benchmarking Deep Reinforcement Learning for Continuous Control
- Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation
- Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning
- Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning