Generating Automatic Curricula Via Self-supervised Active Domain Randomization

Abstract

Goal-directed Reinforcement Learning (RL) traditionally considers an agent interacting with an environment, prescribing a real-valued reward to an agent proportional to the completion of some goal. Goal-directed RL has seen large gains in sample efficiency, due to the ease of reusing or generating new experience by proposing goals. One approach,self-play, allows an agent to "play" against itself by alternatively setting and accomplishing goals, creating a learned curriculum through which an agent can learn to accomplish progressively more difficult goals. However, self-play has been limited to goal curriculum learning or learning progressively harder goals within a single environment. Recent work on robotic agents has shown that varying the environment during training, for example with domain randomization, leads to more robust transfer. As a result, we extend the self-play framework to jointly learn a goal and environment curriculum, leading to an approach that learns the most fruitfu

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyraparthy2020generating

Related papers

• Automatic Goal Generation For Reinforcement Learning Agents (2017)0.00
• Learning Curricula In Open-ended Worlds (2023)0.00
• Replay-guided Adversarial Environment Design (2021)0.00
• Robust Visual Domain Randomization For Reinforcement Learning (2019)0.00
• Task Phasing: Automated Curriculum Learning From Demonstrations (2022)5.24
• How To Pick The Domain Randomization Parameters For Sim-to-real Transfer Of Reinforcement Learning Policies? (2019)0.00
• Curriculum Learning For Reinforcement Learning Domains: A Framework And Survey (2020)0.00
• Discovering General Reinforcement Learning Algorithms With Adversarial Environment Design (2023)0.00