Blendrl: A Framework For Merging Symbolic And Neural Policy Learning

Abstract

Humans can leverage both symbolic reasoning and intuitive reactions. In contrast, reinforcement learning policies are typically encoded in either opaque systems like neural networks or symbolic systems that rely on predefined symbols and rules. This disjointed approach severely limits the agents' capabilities, as they often lack either the flexible low-level reaction characteristic of neural agents or the interpretable reasoning of symbolic agents. To overcome this challenge, we introduce BlendRL, a neuro-symbolic RL framework that harmoniously integrates both paradigms within RL agents that use mixtures of both logic and neural policies. We empirically demonstrate that BlendRL agents outperform both neural and symbolic baselines in standard Atari environments, and showcase their robustness to environmental changes. Additionally, we analyze the interaction between neural and symbolic policies, illustrating how their hybrid use helps agents overcome each other's limitations.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyshindo2024blendrl

Related papers

• Interpretable End-to-end Neurosymbolic Reinforcement Learning Agents (2024)0.00
• Three Pathways To Neurosymbolic Reinforcement Learning With Interpretable Model And Policy Networks (2024)0.00
• S-REINFORCE: A Neuro-symbolic Policy Gradient Approach For Interpretable Reinforcement Learning (2023)0.00
• Policy Fusion For Adaptive And Customizable Reinforcement Learning Agents (2021)0.00
• "so, Tell Me About Your Policy...": Distillation Of Interpretable Policies From Deep Reinforcement Learning Agents (2025)0.00
• Mitigating Information Loss In Tree-based Reinforcement Learning Via Direct Optimization (2024)0.00
• Flexible Attention-based Multi-policy Fusion For Efficient Deep Reinforcement Learning (2022)2.26
• Blending Imitation And Reinforcement Learning For Robust Policy Improvement (2023)0.00