LGAIMLSep 29, 2018

Generalization and Regularization in DQN

arXiv:1810.00123v3224 citations
Originality Synthesis-oriented
AI Analysis

This addresses generalization issues in deep reinforcement learning for Atari games, but it is incremental as it applies existing regularization methods to DQN.

The paper tackled the problem of poor generalization in DQN policies when evaluated in similar environments, showing that regularization techniques like dropout and L2 can help DQN learn more general features, improving sample efficiency by enabling reuse and fine-tuning.

Deep reinforcement learning algorithms have shown an impressive ability to learn complex control policies in high-dimensional tasks. However, despite the ever-increasing performance on popular benchmarks, policies learned by deep reinforcement learning algorithms can struggle to generalize when evaluated in remarkably similar environments. In this paper we propose a protocol to evaluate generalization in reinforcement learning through different modes of Atari 2600 games. With that protocol we assess the generalization capabilities of DQN, one of the most traditional deep reinforcement learning algorithms, and we provide evidence suggesting that DQN overspecializes to the training environment. We then comprehensively evaluate the impact of dropout and $\ell_2$ regularization, as well as the impact of reusing learned representations to improve the generalization capabilities of DQN. Despite regularization being largely underutilized in deep reinforcement learning, we show that it can, in fact, help DQN learn more general features. These features can be reused and fine-tuned on similar tasks, considerably improving DQN's sample efficiency.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes