Centralized Reward Agent For Knowledge Sharing And Transfer In Multi-task Reinforcement Learning
2024 · Haozhe Ma, Zhengding Luo, Thanh Vinh Vo, et al.
Abstract
Reward shaping is effective in addressing the sparse-reward challenge in reinforcement learning (RL) by providing immediate feedback through auxiliary, informative rewards. Based on the reward shaping strategy, we propose a novel multi-task reinforcement learning framework that integrates a centralized reward agent (CRA) and multiple distributed policy agents. The CRA functions as a knowledge pool, aimed at distilling knowledge from various tasks and distributing it to individual policy agents to improve learning efficiency. Specifically, the shaped rewards serve as a straightforward metric for encoding knowledge. This framework not only enhances knowledge sharing across established tasks but also adapts to new tasks by transferring meaningful reward signals. We validate the proposed method on both discrete and continuous domains, including the representative Meta-World benchmark, demonstrating its robustness in multi-task sparse-reward settings and its effective transferability to uns
Authors
(none)
Tags
Stats
Related papers
- Highly Efficient Self-adaptive Reward Shaping For Reinforcement Learning (2024)0.00
- On The Fundamental Limitations Of Decentralized Learnable Reward Shaping In Cooperative Multi-agent Reinforcement Learning (2025)0.00
- Guiding Multi-agent Multi-task Reinforcement Learning By A Hierarchical Framework With Logical Reward Shaping (2024)0.00
- Multi-granularity Knowledge Transfer For Continual Reinforcement Learning (2024)2.26
- Subgoal-based Reward Shaping To Improve Efficiency In Reinforcement Learning (2021)0.00
- Coordinated Exploration Via Intrinsic Rewards For Multi-agent Reinforcement Learning (2019)0.00
- Knowru: Knowledge Reusing Via Knowledge Distillation In Multi-agent Reinforcement Learning (2021)9.23
- Cautiously-optimistic Knowledge Sharing For Cooperative Multi-agent Reinforcement Learning (2023)5.84