Drama: Mambaを活用したモデルベース強化学習のサンプル効率とパラメータ効率
Drama: Mamba-Enabled Model-Based Reinforcement Learning Is Sample and Parameter Efficient
Mambaをベースにした状態空間モデルで世界モデルを構築し、Atari100kで競争力のある性能を700万パラメータで達成した研究。
著者: Wenlong Wang, Ivana Dusparic, Yucheng Shi, Ke Zhang, Vinny Cahill
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Model-based reinforcement learning (RL) offers a solution to the data inefficiency that plagues most model-free RL algorithms. However, learning a robust world model often requires complex and deep architectures, which are computationally expensive and challenging to train. Within the world model, sequence models play a critical role in accurate predictions, and various architectures have been explored, each with its own challenges. Currently, recurrent neural network (RNN)-based world models struggle with vanishing gradients and capturing long-term dependencies. Transformers, on the other hand, suffer from the quadratic memory and computational complexity of self-attention mechanisms, scaling as $O(n^2)$, where $n$ is the sequence length. To address these challenges, we propose a state space model (SSM)-based world model, Drama, specifically leveraging Mamba, that achieves $O(n)$ memory and computational complexity while effectively capturing long-term dependencies and enabling efficient training with longer sequences. We also introduce a novel sampling method to mitigate the suboptimality caused by an incorrect world model in the early training stages. Combining these techniques, Drama achieves a normalised score on the Atari100k benchmark that is competitive with other state-of-the-art (SOTA) model-based RL algorithms, using only a 7 million-parameter world model. Drama is accessible and trainable on off-the-shelf hardware, such as a standard laptop. Our code is available at https://github.com/realwenlongwang/Drama.git.
関連論文
- テスト時モデルベース強化学習による世界モデルへの記憶の符号化モデルベース強化学習
- 再考:世界モデルにおける比較的想像を通じた探索と計画モデルベース強化学習
- アクションジェット:行動条件付きデータ多様体の局所形状の学習モデルベース強化学習
- 未モデル状態依存性下での学習クリティックによる最適制御モデルベース強化学習
- VIGOR: モデルベース強化学習における潜在空間一貫性によるゼロショット視覚汎化モデルベース強化学習
- 行動なし時系列からの動的埋め込みによる転移可能な方策学習モデルベース強化学習
