Flexible Attention-based Multi-policy Fusion For Efficient Deep Reinforcement Learning

Abstract

Reinforcement learning (RL) agents have long sought to approach the efficiency of human learning. Humans are great observers who can learn by aggregating external knowledge from various sources, including observations from others' policies of attempting a task. Prior studies in RL have incorporated external knowledge policies to help agents improve sample efficiency. However, it remains non-trivial to perform arbitrary combinations and replacements of those policies, an essential feature for generalization and transferability. In this work, we present Knowledge-Grounded RL (KGRL), an RL paradigm fusing multiple knowledge policies and aiming for human-like efficiency and flexibility. We propose a new actor architecture for KGRL, Knowledge-Inclusive Attention Network (KIAN), which allows free knowledge rearrangement due to embedding-based attentive action prediction. KIAN also addresses entropy imbalance, a problem arising in maximum entropy KGRL that hinders an agent from efficiently ex

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keychiu2022flexible

Related papers

• Policy Fusion For Adaptive And Customizable Reinforcement Learning Agents (2021)0.00
• Dynamic Policy Fusion For User Alignment Without Re-interaction (2024)0.00
• Attention-driven Multi-agent Reinforcement Learning: Enhancing Decisions With Expertise-informed Tasks (2024)4.52
• Blendrl: A Framework For Merging Symbolic And Neural Policy Learning (2024)0.00
• MULTIPOLAR: Multi-source Policy Aggregation For Transfer Reinforcement Learning Between Diverse Environmental Dynamics (2019)7.81
• Leveraging Class Abstraction For Commonsense Reinforcement Learning Via Residual Policy Gradient Methods (2022)0.00
• I Know How: Combining Prior Policies To Solve New Tasks (2024)2.26
• Policy Agnostic RL: Offline RL And Online RL Fine-tuning Of Any Class And Backbone (2024)0.00