Replay-Guided Adversarial Environment Design. (arXiv:2110.02439v2 [cs.LG] UPDATED)

Deep reinforcement learning (RL) agents may successfully generalize to new
settings if trained on an appropriately diverse set of environment and task
configurations. Unsupervised Environment Design (UED) is a promising
self-supervised RL paradigm, wherein the free parameters of an underspecified
environment are automatically adapted during training to the agent's
capabilities, leading to the emergence of diverse training environments. Here,
we cast Prioritized Level Replay (PLR), an empirically successful but
theoretically unmotivated method that selectively samples randomly-generated
training levels, as UED. …

arxiv design environment