Leveraging Approximate Symbolic Models For Reinforcement Learning Via Skill Diversity

Abstract

Creating reinforcement learning (RL) agents that are capable of accepting and leveraging task-specific knowledge from humans has been long identified as a possible strategy for developing scalable approaches for solving long-horizon problems. While previous works have looked at the possibility of using symbolic models along with RL approaches, they tend to assume that the high-level action models are executable at low level and the fluents can exclusively characterize all desirable MDP states. Symbolic models of real world tasks are however often incomplete. To this end, we introduce Approximate Symbolic-Model Guided Reinforcement Learning, wherein we will formalize the relationship between the symbolic model and the underlying MDP that will allow us to characterize the incompleteness of the symbolic model. We will use these models to extract high-level landmarks that will be used to decompose the task. At the low level, we learn a set of diverse policies for each possible task subgoal

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyguan2022leveraging

Related papers

• Hierarchical And Interpretable Skill Acquisition In Multi-task Reinforcement Learning (2017)0.00
• Skills: Adaptive Skill Sequencing For Efficient Temporally-extended Exploration (2022)0.00
• Neuroevolution Is A Competitive Alternative To Reinforcement Learning For Skill Discovery (2022)0.00
• Learning Symbolic Representations For Reinforcement Learning Of Non-markovian Behavior (2023)0.00
• Approximating Gradients For Differentiable Quality Diversity In Reinforcement Learning (2022)0.00
• Diversity For Contingency: Learning Diverse Behaviors For Efficient Adaptation And Transfer (2023)0.00
• Skill-aware Mutual Information Optimisation For Generalisation In Reinforcement Learning (2024)0.00
• A Hierarchical Bayesian Approach To Inverse Reinforcement Learning With Symbolic Reward Machines (2022)0.00