RLSS: A Deep Reinforcement Learning Algorithm for Sequential Scene Generation
This addresses scene generation problems for applications like game design and virtual planning, though it is incremental as it builds on existing PPO and greedy search techniques.
The paper tackles sequential scene generation by developing RLSS, a reinforcement learning algorithm that combines PPO with greedy search to reduce action space complexity. The method successfully generates plausible and diverse scenes for indoor planning and Angry Birds levels, converging with large action sets and meeting predefined design objectives.
We present RLSS: a reinforcement learning algorithm for sequential scene generation. This is based on employing the proximal policy optimization (PPO) algorithm for generative problems. In particular, we consider how to effectively reduce the action space by including a greedy search algorithm in the learning process. Our experiments demonstrate that our method converges for a relatively large number of actions and learns to generate scenes with predefined design objectives. This approach is placing objects iteratively in the virtual scene. In each step, the network chooses which objects to place and selects positions which result in maximal reward. A high reward is assigned if the last action resulted in desired properties whereas the violation of constraints is penalized. We demonstrate the capability of our method to generate plausible and diverse scenes efficiently by solving indoor planning problems and generating Angry Birds levels.