A Code

Input preprocessing We convert all images to grayscale and resize to 84x84. It is a convolutional neural network with fixed random weights. In Atari, we use 128 parallel environments, and in Habitat, we use 1 environment, as it does not support multithreading. We use the same hyperparameters as in large scale curiosity: a learning rate of 0.0001 for all models, a discount factor Future prediction and multimodal association can be complementary forms of curiosity. Further work could explore other ways of combining intrinsic rewards, such as switching between the complementary forms.