mlsanityData to 14 Oct 2026

Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning

arXiv 2408.10858 ↗First posted 20 Aug 2024cs.LG cs.AIcited by 1

On the map: Deep reinforcement learning methods → Deep RL algorithms and representations

Abstract (arXiv)

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 unseen tasks.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Deep RL algorithms and representations, one of 15 directions in Deep reinforcement learning methods. Builds on 39 of its 69 references that are in the map. First posted on arXiv 20 Aug 2024.

Builds on

39 of 69 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Highly Efficient Self-Adaptive Reward Shaping for Reinforcement Learning6 Aug
  2. 2024Sharing Knowledge in Multi-Task Deep Reinforcement Learning17 Jan

Other references · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  4. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  7. 2020Gradient Surgery for Multi-Task Learningcited by 1,256
  8. 2018Soft Actor-Critic Algorithms and Applicationscited by 1,240
  9. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  10. 2017Curiosity-driven Exploration by Self-supervised Predictioncited by 1,194
  11. 2018Exploration by Random Network Distillationcited by 993
  12. 2017GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networkscited by 834
25 more
  1. 2016Unifying Count-Based Exploration and Intrinsic Motivationcited by 639
  2. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 512
  3. 2015Policy Distillationcited by 440
  4. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  5. 2016#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learningcited by 309
  6. 2017Count-Based Exploration with Neural Density Modelscited by 257
  7. 2017Distral: Robust Multitask Reinforcement Learningcited by 233
  8. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 178
  9. 2021Multi-Task Reinforcement Learning with Context-based Representationscited by 174
  10. 2022Exploration in Deep Reinforcement Learning: A Surveycited by 166
  11. 2020Multi-Task Reinforcement Learning with Soft Modularizationcited by 143
  12. 2023Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmarkcited by 143
  13. 2018Multi-task Deep Reinforcement Learning with PopArtcited by 141
  14. 2016Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfercited by 127
  15. 2020Survey of Deep Reinforcement Learning for Motion Planning of Autonomous Vehiclescited by 110
  16. 2016Playing FPS Games with Deep Reinforcement Learningcited by 95
  17. 2022PaCo: Parameter-Compositional Multi-Task Reinforcement Learningcited by 46
  18. 2021Self-Supervised Online Reward Shaping in Sparse-Reward Environmentscited by 37
  19. 2020Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Controlcited by 28
  20. 2021How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimationcited by 27
  21. 2020A Decentralized Policy Gradient Approach to Multi-task Reinforcement Learningcited by 25
  22. 2023Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learningcited by 10
  23. 2021Learning to Shape Rewards using a Game of Two Partnerscited by 9
  24. 2020Mutual Information Based Knowledge Transfer Under State-Action Dimension Mismatchcited by 8
  25. 2023Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routingcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026From Suboptimal to Optimal: One-Step Latent Flow Policies for Offline Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025On the Fundamental Limitations of Decentralized Learnable Reward Shaping in Cooperative Multi-Agent Reinforcement Learning
  2. 2026ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
  3. 2024Dense Dynamics-Aware Reward Synthesis: Integrating Prior Experience with Demonstrations
  4. 2025Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning
  5. 2025Logic-based Task Representation and Reward Shaping in Multiagent Reinforcement Learning ↗
  6. 2024Adaptive Reward Design for Reinforcement Learning
  7. 2025Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise
  8. 2024From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge