Exploration with Unreliable Intrinsic Reward in Multi-Agent Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
This paper investigates the use of intrinsic reward to guide exploration in multi-agent reinforcement learning. We discuss the challenges in applying intrinsic reward to multiple collaborative agents and demonstrate how unreliable reward can prevent decentralized agents from learning the optimal policy. We address this problem with a novel framework, Independent Centrally-assisted Q-learning (ICQL), in which decentralized agents share control and an experience replay buffer with a centralized agent. Only the centralized agent is intrinsically rewarded, but the decentralized agents still benefit from improved exploration, without the distraction of unreliable incentives.
Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Jun 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 4; 2023: 2; 2024: 1; 2025: 2.
13 papers.
Sort:
- 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
- 2022Solving Continuous Control via Q-learningcited by 21
- 2022ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Rewardcited by 11
- 2024Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolutioncited by 6
- 2021Cooperative and Competitive Biases for Multi-Agent Reinforcement Learningcited by 5
- 2022Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?cited by 4
- 2021Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learningcited by 3
- 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3
- 2021Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learningcited by 2
- 2022Curiosity-Driven Multi-Agent Exploration with Mixed Objectivescited by 2
- 2025Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertisecited by 1
- 2023SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learningcited by 0
- 2025Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise25 Jul 2025
- 2025Optimistic ε-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning5 Feb 2025
- 2024Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution5 Apr 2024
- 2023A Survey of Historical Learning: Learning Models with Learning History23 Mar 2023
- 2023SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning16 Mar 2023
- 2022Curiosity-Driven Multi-Agent Exploration with Mixed Objectives29 Oct 2022
- 2022Solving Continuous Control via Q-learning22 Oct 2022
- 2022ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward9 Oct 2022
- 2022Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?24 Feb 2022
- 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain14 Sep 2021
- 2021Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning30 Jul 2021
- 2021Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning24 Feb 2021
1 more
- 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domaincited by 57
- 2022Solving Continuous Control via Q-learningcited by 21
- 2022ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Rewardcited by 11
- 2024Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolutioncited by 6
- 2021Cooperative and Competitive Biases for Multi-Agent Reinforcement Learningcited by 5
- 2022Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?cited by 4
- 2021Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learningcited by 3
- 2023A Survey of Historical Learning: Learning Models with Learning Historycited by 3
- 2021Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learningcited by 2
- 2022Curiosity-Driven Multi-Agent Exploration with Mixed Objectivescited by 2
- 2025Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertisecited by 1
- 2023SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learningcited by 0
12 most cited of 13 All 13 (JSON)
- 2025Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise25 Jul 2025
- 2025Optimistic ε-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning5 Feb 2025
- 2024Growing Q-Networks: Solving Continuous Control Tasks with Adaptive Control Resolution5 Apr 2024
- 2023A Survey of Historical Learning: Learning Models with Learning History23 Mar 2023
- 2023SVDE: Scalable Value-Decomposition Exploration for Cooperative Multi-Agent Reinforcement Learning16 Mar 2023
- 2022Curiosity-Driven Multi-Agent Exploration with Mixed Objectives29 Oct 2022
- 2022Solving Continuous Control via Q-learning22 Oct 2022
- 2022ELIGN: Expectation Alignment as a Multi-Agent Intrinsic Reward9 Oct 2022
- 2022Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?24 Feb 2022
- 2021Exploration in Deep Reinforcement Learning: From Single-Agent to Multiagent Domain14 Sep 2021
- 2021Strategically Efficient Exploration in Competitive Multi-agent Reinforcement Learning30 Jul 2021
- 2021Credit Assignment with Meta-Policy Gradient for Multi-Agent Reinforcement Learning24 Feb 2021
12 newest of 13 All 13 (JSON)