Assessing Generalization In Deep Reinforcement Learning

Abstract

Deep reinforcement learning (RL) has achieved breakthrough results on many tasks, but agents often fail to generalize beyond the environment they were trained in. As a result, deep RL algorithms that promote generalization are receiving increasing attention. However, works in this area use a wide variety of tasks and experimental setups for evaluation. The literature lacks a controlled assessment of the merits of different generalization schemes. Our aim is to catalyze community-wide progress on generalization in deep RL. To this end, we present a benchmark and experimental protocol, and conduct a systematic empirical study. Our framework contains a diverse set of environments, our methodology covers both in-distribution and out-of-distribution generalization, and our evaluation includes deep RL algorithms that specifically tackle generalization. Our key finding is that `vanilla' deep RL algorithms generalize better than specialized schemes that were proposed specifically to tackle gen

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypacker2018assessing

Related papers

• Measuring And Characterizing Generalization In Deep Reinforcement Learning (2018)9.76
• Quantifying Generalization In Reinforcement Learning (2018)0.00
• A Survey Analyzing Generalization In Deep Reinforcement Learning (2024)0.00
• The Principle Of Unchanged Optimality In Reinforcement Learning Generalization (2019)0.00
• A Survey On Deep Reinforcement Learning-based Approaches For Adaptation And Generalization (2022)0.00
• Generalizing Skills With Semi-supervised Reinforcement Learning (2016)0.00
• Understanding What Affects The Generalization Gap In Visual Reinforcement Learning: Theory And Empirical Evidence (2024)5.84
• Illuminating Generalization In Deep Reinforcement Learning Through Procedural Level Generation (2018)0.00