Generalization in Reward Learning
Implementing the T-REX Reward Learning algorithm on the OpenAI Procgen Benchmark games
Authors: Anton Makiievskyi, Liang Zhou, Max Chiswick
Note: This is the second of two blog posts (part one). In these posts, we describe a project we undertook to assess the ability of reward learning agents to generalize. The implementation for this project is available on GitHub.
In the first post, we reviewed some fundamental background material and described the inspiration for as well as the aims of our project. In doing so, we discussed a number of papers that served as the launching point for our experiments.
We based our implementations on T-REX [Brown and Goo et al. 2019]. We chose it for its straightforward setup, as…
Generalization in Reward Learning
An overview of reinforcement learning, generalization, and reward learning
Authors: Anton Makiievskyi, Liang Zhou, Max Chiswick
Note: This is the first of two blog posts (part two). In these posts, we describe a project we undertook to assess the ability of reward learning agents to generalize. The implementation for this project is available on GitHub.
This first post will provide a background on reinforcement learning, reward learning, and generalization, as well as summarize the main aims and inspirations for our project. If you have the requisite technical background, feel free to skip the first couple sections.
About Us
We are a team that participated in the 2020 AI Safety Camp (AISC)…
