PettingZoo library accelerates multi-agent reinforcement learning research.
problem Challenges in multi-agent reinforcement learning, especially conceptual models of games.
method Developed PettingZoo library with AEC games model to address multi-agent reinforcement learning challenges.
result AEC games model addresses conceptual issues in multi-agent reinforcement learning environments.
Paper analyzes convergence rates for multi-agent learning in games.
problem Convergence rates for multi-agent learning in games.
method Characterizes finite-time convergence rates for joint OGD learning on λ-cocoercive games and develops adaptive algorithms. result Adaptive algorithms achieve same convergence rates as non-adaptive counterparts.
PPO algorithm converges to global optimality in multi-agent reinforcement learning.
problem Designing statistical guarantees for policy optimization methods in multi-agent reinforcement learning.
method Leveraging a multi-agent performance difference lemma, a localized action value function is used as a descent direction for each local policy, leading to a multi-agent PPO algorithm.
result The multi-agent PPO algorithm converges to the globally optimal policy at a sublinear rate under standard regularity conditions.
JPS improves joint policies for multi-agent collaboration in imperfect information games.
problem Learning good joint policies for multi-agent collaboration with imperfect information.
method Decomposes global changes to localized policy changes, iteratively improving joint policies without re-evaluating the entire game.
result JPS improves solutions provided by unilateral approaches and outperforms algorithms designed for collaborative policy learning.
New approach tackles non-stationary multi-agent games with black-box methods.
problem Challenges in learning equilibria in non-stationary multi-agent systems.
method Versatile black-box approach applicable to various games, including general-sum, potential, and Markov games.
result Achieves optimal regret bounds for non-stationary games, with or without knowledge of total variation.
Expands MFGs to handle real-world asymmetric multi-agent games efficiently.
problem Applying mean-field games to real-world, heterogeneous multi-agent systems.
method Develops a method to symmetrize and extend finite-player games to infinite-player MFGs, proving approximation bounds and convergence guarantees.
result TD learning converges to approximate Nash equilibria in finite-sample settings, enabling symmetrized learning without explicit MFG models.
Transformers learn to play games in-context, proving Nash equilibrium.
problem Understanding in-context game-playing capabilities of pre-trained transformers.
method Theoretical guarantees and constructional results for transformer architecture in multi-agent games.
result Pre-trained transformers can learn Nash equilibrium in-context for two-player zero-sum games.
We show by counterexample that policy-gradient algorithms have no guarantees of even local convergence to Nash equilibria in continuous action and state space multi-agent settings. To do so, we analyze gradient-play in N-player general-sum linear quadratic games, a classic game setting which is recently emerging as a b…
The paper simplifies multi-agent RL dynamics in finite-state Markov games using homogenization.
problem Approximating complex multi-agent reinforcement learning dynamics in finite-state Markov games.
method Rescaling learning process by reducing learning rate and increasing update frequency, proving convergence to an ODE.
result The rescaled process converges to an ODE that approximates the agent's learning dynamics.
Recent breakthroughs in AI for multi-agent games like Go, Poker, and Dota, have seen great strides in recent years. Yet none of these games address the real-life challenge of cooperation in the presence of unknown and uncertain teammates. This challenge is a key game mechanism in hidden role games. Here we develop the …
Deep neural network solves large multi-agent games for Markovian Nash equilibrium.
problem Finding Markovian Nash equilibrium in large multi-agent stochastic differential games.
method Reformulate as decoupled decision problems, solve iteratively using deep BSDE method.
result Proposed algorithm accurately finds Nash equilibrium in large games.
AEC Games model represents software MARL environments better than POSGs.
problem POSGs are conceptually unsuitable for software MARL environments.
method Introduced AEC Games model as an equivalent to POSGs.
result AEC Games model is more representative of software MARL environments.
We report on a technique based on multi-agent games which has potential use in the prediction of future movements of financial time-series. A third-party game is trained on a black-box time-series, and is then run into the future to extract next-step and multi-step predictions. In addition to the possibility of identif…
Framework for multi-agent RL with human feedback in a Snake game.
problem Improving multi-agent reinforcement learning with human feedback.
method Developed a simulated game environment for offline model training and online competitions. Introduced HILL methods and reward manipulation heuristics.
result Agents with HILL methods outperform those without in online competitions.
New algorithm finds Nash equilibrium in multi-agent games.
problem Extending RL theory to multi-agent settings with large state spaces.
method Proposes an algorithm using an exploiter to find Nash equilibrium policies.
result Proves finding Nash equilibrium is possible with polynomial samples.
Paper tackles delays in multi-agent reinforcement learning, improving performance.
problem Challenges in reinforcement learning due to delays in real-world systems.
method Proposes a novel framework for multi-agent reinforcement learning with delays, using Delay-Aware Markov Games and centralized-decentralized training.
result Demonstrates significant improvement in performance with delay-aware multi-agent reinforcement learning.
The paper explores when and why value decomposition algorithms work in cooperative multi-agent reinforcement learning.
problem The applicability and convergence properties of value decomposition algorithms in cooperative multi-agent reinforcement learning are unclear.
method The paper introduces decomposable games and proves that applying the multi-agent fitted Q-Iteration algorithm leads to an optimal Q-function in these games.
result The paper offers theoretical insights into when and why value decomposition algorithms converge in cooperative multi-agent reinforcement learning.
The paper analyzes strategic interactions in a multi-agent reinsurance chain using game theory.
problem Strategic behavior and competition among insurers and reinsurers in a multi-layer reinsurance chain.
method Employed Stackelberg differential games and non-zero-sum game models to characterize strategic interactions. Used dynamic programming and game theory to derive equilibrium strategies for investment and reinsurance.
result Intensified competition leads to reduced safety loadings in reinsurance contracts.
This work tackles robust RL in multi-agent settings, improving sample efficiency.
problem Overcoming environmental uncertainties in multi-agent reinforcement learning.
method Proposes DRNVI, a sample-efficient algorithm for learning robust equilibria in RMGs.
result Establishes near-optimal sample complexity for solving RMGs.
Paper optimizes multi-agent learning in Markov games with generative model.
problem Learning Nash or CCE equilibria in multi-agent Markov games.
method Develops \myalg~algorithm and adaptive sampling scheme using FTRL method.
result Minimax-optimal learning of CCE with minimal samples.
Study on multi-agent decision making complexity, showing sample efficiency gaps.
problem Understanding sample efficiency in multi-agent decision making.
method General framework for interactive decision making, focusing on equilibrium computation.
result No 'reasonable' complexity measure can close gaps between single and multiple agents.
Paper introduces metrics for evaluating multi-agent policies using best response dynamics.
problem Evaluation and ranking of multi-agent policies in reinforcement learning.
method Adopting strict best response dynamics (SBRD) to model selfish behaviors, proposing perturbed SBRD for dynamic and non-stationary settings.
result Proposed perturbed SBRD can observe policies with maximum metrics and differ from optimal by any given tolerance.
Decentralised optimisation tasks are important components of multi-agent systems. These tasks can be interpreted as n-player potential games: therefore game-theoretic learning algorithms can be used to solve decentralised optimisation tasks. Fictitious play is the canonical example of these algorithms. Nevertheless fic…
The paper analyzes reinsurance strategies in a competitive multi-agent system.
problem Strategic interactions and competitive behavior in multi-layer reinsurance chains.
method Stochastic differential games and non-zero-sum game models to characterize strategic interactions. Dynamic programming and game theory to derive equilibrium strategies.
result Intensified competition reduces safety loadings in reinsurance contracts.
Improved model-based reinforcement learning for multi-agent Markov games.
problem Suboptimal sample complexity for model-based algorithms in multi-agent reinforcement learning.
method Optimistic Nash Value Iteration (Nash-VI) for two-player zero-sum Markov games.
result First model-based algorithm matching information-theoretic lower bound with improved sample complexity.
Study multi-agent RL in OTC markets, learning from agents' interactions.
problem Designing efficient RL solutions for OTC market interactions.
method Parameterized reward functions, shared policy learning, RL calibration.
result Agents learn to balance hedging and skewing in market simulations.
New algorithm tackles multi-agent reinforcement learning with optimal convergence rate.
problem Multi-agent reinforcement learning with large state spaces and linear function approximations.
method Refined AVLPR framework with data-dependent pessimistic estimation and action-dependent bonuses.
result First algorithm with optimal O(T−1/2) convergence rate and no poly(Amax) dependency. Algorithm finds ε-equilibrium policies for multi-agent Markov games with hidden low-rank structure.
problem Designing efficient algorithms for multi-agent Markov games with unknown representation and hidden low-rank structure.
method Model-based and model-free approaches using representation learning to construct an effective representation from data.
result Achieves poly(H,d,A,1/ε) sample complexity for both model-based and model-free approaches. Study online learning in unknown Markov games with sublinear regret.
problem Online learning in unknown Markov games with unobservable opponents.
method Introduced an algorithm achieving sublinear regret against the minimax value.
result First sublinear regret bound for unknown Markov games, independent of action spaces size.
We formulate a general framework for competitive gradient-based learning that encompasses a wide breadth of multi-agent learning algorithms, and analyze the limiting behavior of competitive gradient-based learning algorithms using dynamical systems theory. For both general-sum and potential games, we characterize a non…
This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training. We propose two new games with concealed information and complex, non-transitive reward structure (think rock/paper/scissors). It turns out that mos…
Graphs help agents learn emergent communication.
problem Learning robust communication protocols in multi-agent systems.
method Graph convolutional networks to model emergent language and cooperation.
result Agents learn to generalize beyond training samples, revealing true factors of variation.
Imitation learning algorithms can be used to learn a policy from expert demonstrations without access to a reward signal. However, most existing approaches are not applicable in multi-agent settings due to the existence of multiple (Nash) equilibria and non-stationary environments. We propose a new framework for multi-…
New NPG variants ensure parameter convergence in multi-agent learning.
problem Non-convergence of parameters in NPG for multi-agent learning.
method Proposed variants of NPG for multi-agent learning scenarios.
result Global last-iterate parameter convergence guarantees in various multi-agent learning settings.
CollaQ improves multi-agent performance in StarCraft by 40% with fewer samples.
problem Limited generalization and high training rounds in multi-agent reinforcement learning.
method Formulates multi-agent collaboration as joint optimization on reward assignment, decomposes Q-function into self and interactive terms, and uses MARA loss.
result Improves win rate by 40% in StarCraft maps with same number of samples compared to state-of-the-art techniques.
A method to train multi-agent reinforcement learning models without intrinsic rewards.
problem Training multi-agent reinforcement learning models with sparse rewards is challenging.
method A learning-based exploration strategy using variational graph autoencoder to generate initial states.
result The method improves the training and performance of multi-agent reinforcement learning models.
Proposes a game-theoretic framework for ML trust regulation.
problem Lack of coordination between ML model builders and regulators.
method Formulates trustworthy ML as a multi-objective multi-agent optimization problem and introduces regulation games and ParetoPlay.
result Enables efficient enforcement of ML model specifications without discouraging participation.
LAFF algorithm balances adaptability and non-exploitability in repeated games.
problem Low regret in repeated games against unknown opponent classes.
method LAFF algorithm searches within sub-algorithms optimal for each opponent class and uses a punishment policy for exploitation.
result LAFF guarantees sublinear regret uniformly over possible opponents, except exploitative ones, for which it guarantees linear regret.
NOHD optimizes multi-agent systems by decomposing dynamics into irrotational and solenoidal components.
problem Non-stationarity and conflicting interests in multi-agent learning problems.
method NOHD (Newton Optimization on Helmholtz Decomposition) decomposes system dynamics into irrotational and solenoidal components.
result NOHD ensures quadratic convergence in purely irrotational and solenoidal systems and attracts to stable fixed points in general multi-agent systems.
The paper addresses human-like decision-making in multi-agent systems using bounded risk-sensitive Markov Games.
problem Modeling human-like decision-making in multi-agent systems with risk-seeking and loss-aversion behaviors.
method Forward policy design and inverse reward learning with iterative reasoning and cumulative prospect theory.
result The proposed algorithms demonstrate both risk-averse and risk-seeking behaviors in multi-agent systems.
A new method simulates large, diverse populations of learning agents evolving in games.
problem Limited scalability and efficiency of Multi-Agent Reinforcement Learning.
method Parallelizable implementation of Policy Gradient and Opponent-Learning Awareness for evolutionary simulations.
result Simulated large, diverse populations of learning agents evolve under various strategies.
A new multi-agent learning method improves performance in complex games.
problem Performance gap between MAPG and value-based multi-agent approaches.
method Introduces value function decomposition into multi-agent actor-critic framework for off-policy learning.
result DOP significantly outperforms state-of-the-art multi-agent reinforcement learning algorithms.
This work presents a game-theoretic method for AVs that handles imperfect communication and individual rewards.
problem Real-time, imperfect communication and individual rewards in multi-agent interactions.
method Game-theoretic approach that allows for imperfect communication and individual rewards.
result More realistic assumptions lead to better reward inference and prediction of future actions.
Proposes a deep learning method for solving complex financial games with delays.
problem Financial modeling with multi-agent interactions and delayed effects.
method Parameterizes controls using recurrent neural networks and trains them with modified fictitious play.
result Demonstrates effectiveness on finance problems with known solutions and new problems with derived Nash equilibria.
Agents learn to give rewards to others in a shared learning environment.
problem How to encourage cooperation among RL agents in a shared environment.
method Each agent learns a reward function to influence others, optimizing for its own and others' extrinsic objectives.
result Agents significantly outperform standard RL in Markov games, often finding near-optimal division of labor.
New MARL algorithms resolve the curse of multiagency with function approximation.
problem Challenges in Multi-Agent Reinforcement Learning (MARL) due to the curse of multiagency.
method V-Learning with Policy Replay and Decentralized Optimistic Policy Mirror Descent.
result First polynomial sample complexity results for learning approximate Coarse Correlated Equilibria (CCEs) of Markov Games under decentralized linear function approximation.
Hierarchical MARL learns complementary skills for team coordination.
problem Creating intelligent agents that coordinate like human sports teams.
method Two-level hierarchical MARL with unsupervised skill discovery.
result Emergence of useful and complementary skills in team games.
This paper optimizes model-based RL for two-player zero-sum games with near-optimal sample complexity.
problem Optimizing model-based reinforcement learning for two-player zero-sum games with minimal samples.
method Model-based reinforcement learning approach for two-player discounted zero-sum Markov games with a generative model.
result Achieves a sample complexity of ildeO(∣S∣∣A∣∣B∣(1−γ)−3ε−2) for finding the Nash equilibrium and ε-NE policies.