Behavior Cloning in OpenAI using Case Based Reasoning
This work is incremental, offering a tool for benchmarking behavior cloning in reinforcement learning environments.
The paper tackled the problem of implementing behavior cloning in OpenAI Gym by interfacing the jLOAF platform, which uses Case-Based Reasoning, and found that it provides a baseline for comparison and identifies strengths and weaknesses in handling environmental complexity.
Learning from Observation (LfO), also known as Behavioral Cloning, is an approach for building software agents by recording the behavior of an expert (human or artificial) and using the recorded data to generate the required behavior. jLOAF is a platform that uses Case-Based Reasoning to achieve LfO. In this paper we interface jLOAF with the popular OpenAI Gym environment. Our experimental results show how our approach can be used to provide a baseline for comparison in this domain, as well as identify the strengths and weaknesses when dealing with environmental complexity.