Experience Sharing Between Cooperative Reinforcement Learning Agents

Abstract

The idea of experience sharing between cooperative agents naturally emerges from our understanding of how humans learn. Our evolution as a species is tightly linked to the ability to exchange learned knowledge with one another. It follows that experience sharing (ES) between autonomous and independent agents could become the key to accelerate learning in cooperative multiagent settings. We investigate if randomly selecting experiences to share can increase the performance of deep reinforcement learning agents, and propose three new methods for selecting experiences to accelerate the learning process. Firstly, we introduce Focused ES, which prioritizes unexplored regions of the state space. Secondly, we present Prioritized ES, in which temporal-difference error is used as a measure of priority. Finally, we devise Focused Prioritized ES, which combines both previous approaches. The methods are empirically validated in a control problem. While sharing randomly selected experiences between

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keysouza2019experience

Related papers

• Selectively Sharing Experiences Improves Multi-agent Reinforcement Learning (2023)4.61
• Shared Experience Actor-critic For Multi-agent Reinforcement Learning (2020)0.00
• Selective Experience Sharing In Reinforcement Learning Enhances Interference Management (2025)0.00
• Cautiously-optimistic Knowledge Sharing For Cooperative Multi-agent Reinforcement Learning (2023)5.84
• Collaborative Training Of Heterogeneous Reinforcement Learning Agents In Environments With Sparse Rewards: What And When To Share? (2022)6.34
• Prioritized Guidance For Efficient Multi-agent Reinforcement Learning Exploration (2019)0.00
• Settling Decentralized Multi-agent Coordinated Exploration By Novelty Sharing (2024)4.52
• Improved Reinforcement Learning In Cooperative Multi-agent Environments Using Knowledge Transfer (2021)0.00