Do Agents Dream of Electric Sheep?: Improving Generalization in Reinforcement Learning through Generative Learning

arXiv:2403.07979v1 Announce Type: new
Abstract: The Overfitted Brain hypothesis suggests dreams happen to allow generalization in the human brain. Here, we ask if the same is true for reinforcement learning agents as well. Given limited experience in a real environment, we use imagination-based reinforcement learning to train a policy on dream-like episodes, where non-imaginative, predicted trajectories are modified through generative augmentations. Experiments on four ProcGen environments show that, compared to classic imagination and offline training on collected experience, our method …

abstract agents arxiv brain cs.ai cs.lg dreams electric environment experience generative human hypothesis imagination reinforcement reinforcement learning through true type