夢から適応へ:潜在コンテキスト想像とMDP想像によるメタ強化学習
Dream to Adapt: Meta Reinforcement Learning by Latent Context Imagination and MDP Imagination
メタ強化学習において、学習済み潜在コンテキスト空間の補間と生成的世界モデルによる想像を組み合わせ、少ない実タスクとデータで効率的に新規タスクへ適応する手法MetaDreamerを提案。
著者: Lu Wen, Songan Zhang, H. Eric Tseng, Huei Peng
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Meta reinforcement learning (Meta RL) has been amply explored to quickly learn an unseen task by transferring previously learned knowledge from similar tasks. However, most state-of-the-art algorithms require the meta-training tasks to have a dense coverage on the task distribution and a great amount of data for each of them. In this paper, we propose MetaDreamer, a context-based Meta RL algorithm that requires less real training tasks and data by doing meta-imagination and MDP-imagination. We perform meta-imagination by interpolating on the learned latent context space with disentangled properties, as well as MDP-imagination through the generative world model where physical knowledge is added to plain VAE networks. Our experiments with various benchmarks show that MetaDreamer outperforms existing approaches in data efficiency and interpolated generalization.
