Related papers: Joint Policy Search for Multi-agent Collaboration …
Trajectory planning involving multi-agent interactions has been a long-standing challenge in the field of robotics, primarily burdened by the inherent yet intricate interactions among agents. While game-theoretic methods are widely…
Training multi-agent systems (MAS) to achieve realistic equilibria gives us a useful tool to understand and model real-world systems. We consider a general sum partially observable Markov game where agents of different types share a single…
Bid optimization for online advertising from single advertiser's perspective has been thoroughly investigated in both academic research and industrial practice. However, existing work typically assume competitors do not change their bids,…
Over these years, multi-agent reinforcement learning has achieved remarkable performance in multi-agent planning and scheduling tasks. It typically follows the self-play setting, where agents are trained by playing with a fixed group of…
With the rise of online e-commerce platforms, more and more customers prefer to shop online. To sell more products, online platforms introduce various modules to recommend items with different properties such as huge discounts. A web page…
Proximal Policy Optimization (PPO) is a ubiquitous on-policy reinforcement learning algorithm but is significantly less utilized than off-policy learning algorithms in multi-agent settings. This is often due to the belief that PPO is…
Collaboration is crucial for reaching collective goals. However, its effectiveness is often undermined by the strategic behavior of individual agents -- a fact that is captured by a high Price of Stability (PoS) in recent literature [Blum…
Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual…
Effective coordination of agents actions in partially-observable domains is a major challenge of multi-agent systems research. To address this, many researchers have developed techniques that allow the agents to make decisions based on…
In this paper I present several algorithmic techniques for improving the decision process of multiple types of agents behaving in environments where their interests are in conflict. The interactions between the agents are modelled by using…
Public goods games represent insightful settings for studying incentives for individual agents to make contributions that, while costly for each of them, benefit the wider society. In this work, we adopt the perspective of a central planner…
In the case of the two-person zero-sum stochastic game with a central controller, this paper proposes a best collaborative behavior search and selection algorithm based on reinforcement learning, in response to how to choose the best…
Accurate detection of errors in large language models (LLM) responses is central to the success of scalable oversight, or providing effective supervision to superhuman intelligence. Yet, self-diagnosis is often unreliable on complex tasks…
Policy optimization methods with function approximation are widely used in multi-agent reinforcement learning. However, it remains elusive how to design such algorithms with statistical guarantees. Leveraging a multi-agent performance…
In collaborative goal-oriented settings, the participants are not only interested in achieving a successful outcome, but do also implicitly negotiate the effort they put into the interaction (by adapting to each other). In this work, we…
Two-player, constant-sum games are well studied in the literature, but there has been limited progress outside of this setting. We propose Joint Policy-Space Response Oracles (JPSRO), an algorithm for training agents in n-player,…
Mean field games (MFGs) are a promising framework for modeling the behavior of large-population systems. However, solving MFGs can be challenging due to the coupling of forward population evolution and backward agent dynamics. Typically,…
Recent advances in deep reinforcement learning (RL) have led to considerable progress in many 2-player zero-sum games, such as Go, Poker and Starcraft. The purely adversarial nature of such games allows for conceptually simple and…
This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm. Previous research with a related approach in continuous…
We present a framework for computing approximate mixed-strategy Nash equilibria of continuous-action games. It is a modification of the traditional double oracle algorithm, extended to multiple players and continuous action spaces. Unlike…