Neuroevolution Is A Competitive Alternative To Reinforcement Learning For Skill Discovery

Abstract

Deep Reinforcement Learning (RL) has emerged as a powerful paradigm for training neural policies to solve complex control tasks. However, these policies tend to be overfit to the exact specifications of the task and environment they were trained on, and thus do not perform well when conditions deviate slightly or when composed hierarchically to solve even more complex tasks. Recent work has shown that training a mixture of policies, as opposed to a single one, that are driven to explore different regions of the state-action space can address this shortcoming by generating a diverse set of behaviors, referred to as skills, that can be collectively used to great effect in adaptation tasks or for hierarchical planning. This is typically realized by including a diversity term - often derived from information theory - in the objective function optimized by RL. However these approaches often require careful hyperparameter tuning to be effective. In this work, we demonstrate that less widely-

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keychalumeau2022neuroevolution

Related papers

• Collaborative Evolutionary Reinforcement Learning (2019)0.00
• Hypothesis-driven Skill Discovery For Hierarchical Deep Reinforcement Learning (2019)2.26
• Skills: Adaptive Skill Sequencing For Efficient Temporally-extended Exploration (2022)0.00
• Evolutionary Reinforcement Learning: A Survey (2023)13.93
• Skill-critic: Refining Learned Skills For Hierarchical Reinforcement Learning (2023)7.50
• Multitask Neuroevolution For Reinforcement Learning With Long And Short Episodes (2022)0.00
• Combining Evolution And Deep Reinforcement Learning For Policy Search: A Survey (2022)12.25
• Leveraging Approximate Symbolic Models For Reinforcement Learning Via Skill Diversity (2022)0.00