Increasingly Complex Environments in Deep Reinforcement Learning
Oskar Eriksson, Mattias Larsson · KTH Publication Database DiVA (KTH Royal Institute of Technology) · 2019
In this thesis, we used deep reinforcement learning to train autonomous agents and evaluated the impact of increasing the complexity of the training environment over time. This was compared to using a fixed complexity. Also, we investigated the impact of using a pre-trained agent as a starting point for training in an environment with a different complexity, compared to an untrained agent. The scope was limited to only training and analyzing agents playing a variant of the 2D game Snake. Random obstacles were placed on the map, and complexity corresponds to the amount of obstacles. Performance was measured in terms of eaten fruits. The results showed benefits in overall performance for the agent trained in increasingly complex environments. With regard to previous research, it was concluded that this seems to hold generally, but more research is needed on the topic. Also, the results displayed benefits of using a pre-trained model as a starting point for training in a different complexity environment, which was hypothesized.