This repo is a bunch of experiments for an independent study, mostly to keep all of my experiments/code/papers in one place. All models/learning is done with Stable Baselines, and trained on OpenAI Gym environments.
Relevant reading:
- Learning Generalized Reactive Policies using Deep Neural Networks
- [Learning to Design Games: Strategic Environments in Reinforcement Learning](Learning to Design Games: Strategic Environments in Reinforcement Learning)
- Data-Driven Sokoban Puzzle Generation with MCTS
- Uncertainty-sensitive Learning and Planning with Ensembles
- Automated Playtesting
- Evolving Personas
- Procedural Content Generation Survey
- Maximum Entropy Inverse Reinforcement Learning
- Multi-Objective Level Generator with Marahel