Generalization And Regularization In DQN

Abstract

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 \(ℓ₂\) 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 f

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyfarebrother2018generalization

Related papers

• Regularization Matters In Policy Optimization (2019)2.68
• Assessing Generalization In Deep Reinforcement Learning (2018)0.00
• Illuminating Generalization In Deep Reinforcement Learning Through Procedural Level Generation (2018)0.00
• Measuring And Characterizing Generalization In Deep Reinforcement Learning (2018)9.76
• Convergent And Efficient Deep Q Network Algorithm (2021)0.00
• Quantifying Generalization In Reinforcement Learning (2018)0.00
• Dynamics Generalization Via Information Bottleneck In Deep Reinforcement Learning (2020)0.00
• A Survey Analyzing Generalization In Deep Reinforcement Learning (2024)0.00