Improving Performance In Reinforcement Learning By Breaking Generalization In Neural Networks

Abstract

Reinforcement learning systems require good representations to work well. For decades practical success in reinforcement learning was limited to small domains. Deep reinforcement learning systems, on the other hand, are scalable, not dependent on domain specific prior knowledge and have been successfully used to play Atari, in 3D navigation from pixels, and to control high degree of freedom robots. Unfortunately, the performance of deep reinforcement learning systems is sensitive to hyper-parameter settings and architecture choices. Even well tuned systems exhibit significant instability both within a trial and across experiment replications. In practice, significant expertise and trial and error are usually required to achieve good performance. One potential source of the problem is known as catastrophic interference: when later training decreases performance by overriding previous learning. Interestingly, the powerful generalization that makes Neural Networks (NN) so effective in bat

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyghiassian2020improving

Related papers

• A Survey Analyzing Generalization In Deep Reinforcement Learning (2024)0.00
• Dynamics Generalization Via Information Bottleneck In Deep Reinforcement Learning (2020)0.00
• Measuring And Characterizing Generalization In Deep Reinforcement Learning (2018)9.76
• Illuminating Generalization In Deep Reinforcement Learning Through Procedural Level Generation (2018)0.00
• Generalization And Regularization In DQN (2018)0.00
• Generalization Through The Lens Of Learning Dynamics (2022)0.00
• Understanding What Affects The Generalization Gap In Visual Reinforcement Learning: Theory And Empirical Evidence (2024)5.84
• Improving Generalization On The Procgen Benchmark With Simple Architectural Changes And Scale (2024)0.00