Interpretable End-to-end Neurosymbolic Reinforcement Learning Agents

Abstract

Deep reinforcement learning (RL) agents rely on shortcut learning, preventing them from generalizing to slightly different environments. To address this problem, symbolic method, that use object-centric states, have been developed. However, comparing these methods to deep agents is not fair, as these last operate from raw pixel-based states. In this work, we instantiate the symbolic SCoBots framework. SCoBots decompose RL tasks into intermediate, interpretable representations, culminating in action decisions based on a comprehensible set of object-centric relational concepts. This architecture aids in demystifying agent decisions. By explicitly learning to extract object-centric representations from raw states, object-centric RL, and policy distillation via rule extraction, this work places itself within the neurosymbolic AI paradigm, blending the strengths of neural networks with symbolic AI. We present the first implementation of an end-to-end trained SCoBot, separately evaluate of i

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keygrandien2024interpretable

Related papers

• Blendrl: A Framework For Merging Symbolic And Neural Policy Learning (2024)0.00
• Systematic Generalisation Through Task Temporal Logic And Deep Reinforcement Learning (2020)0.00
• End-to-end Neuro-symbolic Reinforcement Learning With Textual Explanations (2024)0.00
• S-REINFORCE: A Neuro-symbolic Policy Gradient Approach For Interpretable Reinforcement Learning (2023)0.00
• Three Pathways To Neurosymbolic Reinforcement Learning With Interpretable Model And Policy Networks (2024)0.00
• Simplified Action Decoder For Deep Multi-agent Reinforcement Learning (2019)4.03
• "so, Tell Me About Your Policy...": Distillation Of Interpretable Policies From Deep Reinforcement Learning Agents (2025)0.00
• Social Interpretable Reinforcement Learning (2024)3.58