Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments

Abstract

We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments. To do so, we study how a teacher algorithm can learn to generate a learning curriculum, whereby it sequentially samples parameters controlling a stochastic procedural generation of environments. Because it does not initially know the capacities of its student, a key challenge for the teacher is to discover which environments are easy, difficult or unlearnable, and in what order to propose them to maximize the efficiency of learning over the learnable ones. To achieve this, this problem is transformed into a surrogate continuous bandit problem where the teacher samples environments in order to maximize absolute learning progress of its student. We present a new algorithm modeling absolute learning progress with Gaussian mixture models (ALP-GMM). We also adapt existing algorithms and provide a complete study in the context of DRL. Using parameterized variants of the BipedalWalker environment, we study their efficiency to personalize a learning curriculum for different learners (embodiments), their robustness to the ratio of learnable/unlearnable environments, and their scalability to non-linear and high-dimensional parameter spaces. Videos and code are available at https://github.com/flowersteam/teachDeepRL.

arXiv commentAccepted at CoRL 2019

References in corpus (5)

• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots
• Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning
• Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
• Multi-Armed Bandits for Intelligent Tutoring Systems

Cited by in corpus (6)

• Automatic Curriculum Learning through Value Disagreement
• Solving Compositional Reinforcement Learning Problems via Task Reduction
• Automated Play-Testing Through RL Based Human-Like Play-Styles Generation
• Battlesnake Challenge: A Multi-agent Reinforcement Learning Playground with Human-in-the-loop
• Discovering Generalizable Skills via Automated Generation of Diverse Tasks
• Trying AGAIN instead of Trying Longer: Prior Learning for Automatic Curriculum Learning