This work tackles uncertainty in multi-agent multi-modal trajectory forecasting.
problem Measuring and ranking uncertainty in multi-agent multi-modal trajectory forecasting.
method Proposes collaborative uncertainty (CU) and a CU-aware regression framework.
result The CU-aware regression framework improves SOTA systems' performances.
Improves neural relational inference for dynamic multi-agent trajectories.
problem Limited accuracy of NRI in short output sequences for relational inference in multi-agent trajectories.
method Proposes DYnamic multi-AgentRelational Inference (DYARI) model to handle changing interactions over time.
result DYARI model outperforms NRI in dynamic relational inference tasks.
Model predicts multi-agent trajectories using a differentiable simulator.
problem Predicting future positions of multiple interacting agents.
method Conditional recurrent variational neural networks (CVRNNs) with a kinematic bicycle model.
result Achieves state-of-the-art results on INTERACTION dataset.
This work enables UAVs to autonomously form desired trajectories without needing a central plan.
problem Autonomous formation of complex trajectories in UAVs.
method Decentralized control system using geometric embeddings.
result Quadcopters self-organize into desired trajectories while maintaining separation.
We study the problem of training sequential generative models for capturing coordinated multi-agent trajectory behavior, such as offensive basketball gameplay. When modeling such settings, it is often beneficial to design hierarchical models that can capture long-term coordination using intermediate variables. Furtherm…
Study differential privacy in multi-agent RL, achieving efficient and private learning.
problem Protecting sensitive data in multi-agent reinforcement learning.
method Extending DP definitions to two-player games, designing an efficient algorithm with privatized bonuses.
result Achieved trajectory-wise differential privacy in multi-agent RL, improving regret bounds.
CODA resolves coordination issues in offline multi-agent reinforcement learning.
problem Coordination failure in offline multi-agent reinforcement learning.
method Diffusion-based multi-agent trajectory generator for data augmentation.
result CODA resolves coordination pathologies in continuous polynomial games and complex benchmarks.
We propose a method to model multi-agent behaviors with limited observation and mechanical constraints.
problem Modeling real-world multi-agent behaviors with limited observation and mechanical constraints.
method Decentralized generative models with partial observation and mechanical constraints based on hierarchical variational recurrent neural networks.
result Our method effectively models and predicts biologically plausible behaviors with minimal constraint violations.
MA-COPP predicts multi-agent system outcomes using data from a different policy, with probabilistic guarantees.
problem Predicting outcomes in multi-agent systems using data from a different policy.
method Conformal prediction framework applied to multi-agent systems, avoiding exhaustive search.
result Achieves probabilistic guarantees for multi-agent system predictions.
Policy-gradient method controls multiple non-cohesive targets.
problem Controlling multiple non-cohesive targets in a decentralized manner.
method Proximal Policy Optimization for target selection and driving.
result Effective control of non-cohesive targets without prior dynamics knowledge.
One-shot path planning for multiple agents using neural networks.
problem Efficiently generating optimal or near-optimal paths for multiple agents in robotics.
method Utilizes fully convolutional neural networks for one-shot multi-agent path planning.
result Demonstrates successful generation of optimal or near-optimal paths in over 85% of cases for multi-path planning.
AgensFlow learns multi-agent coordination policies from experience.
problem Difficult coordination choices in multi-agent systems built on LLMs.
method Online policy learning from repeated trajectories, treating decisions as learnable.
result Learned routing improves coordination-heavy workflows over static wiring.
Paper proposes learning system dynamics from irregularly-sampled partial observations.
problem Capturing dynamics of multi-agent systems with irregular and partial observations.
method LG-ODE, a latent ordinary differential equation model using graph neural networks and neuralODE.
result Demonstrates effectiveness on motion capture, spring system, and charged particle datasets.
REFIL learns from imagined sub-group interactions to improve multi-agent reinforcement learning.
problem Learning efficiency in multi-agent reinforcement learning settings.
method Randomized Entity-wise Factorization (REFIL) approach.
result REFIL outperforms all strong baselines in challenging multi-task StarCraft settings.
Human players in professional team sports achieve high level coordination by dynamically choosing complementary skills and executing primitive actions to perform these skills. As a step toward creating intelligent agents with this capability for fully cooperative multi-agent settings, we propose a two-level hierarchica…
Proposes ABIDES-Gym for financial markets simulation.
problem Training multi-agent systems in financial markets.
method Wrapping DEMAS into OpenAI Gym framework.
result Developed two financial markets OpenAI Gym environments.
Study on market instability in multi-agent trading with price impact and transaction costs.
problem Analyzing market instability in multi-agent trading with price impact and transaction costs.
method Analytical and numerical methods to study Nash equilibria and stability conditions.
result Conditions on model parameters determine market stability, including scaling of market impact and transaction cost.
A multi-agent system is trialed as a means of crowd-sourcing inexpensive but high quality streams of predictions. Each agent is a microservice embodying statistical models and endowed with economic self-interest. The ability to fork and modify simple agents is granted to a large number of employees in a firm and empiri…
Temporal prediction is critical for making intelligent and robust decisions in complex dynamic environments. Motion prediction needs to model the inherently uncertain future which often contains multiple potential outcomes, due to multi-agent interactions and the latent goals of others. Towards these goals, we introduc…
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.
Safe-M3-UCRL learns safe policies for multi-agent systems with global constraints.
problem Global constraints in mean-field reinforcement learning for multi-agent systems.
method Safe-M3-UCRL uses epistemic uncertainty and log-barrier approach to ensure constraints satisfaction. result Safe-M3-UCRL learns safe policies for multi-agent systems with global constraints. This research tackles information design in multi-agent reinforcement learning.
problem Designing information to influence other adaptive agents in a non-stationary environment.
method Formulated Markov signaling game, introduced signaling gradient and extended obedience constraints.
result Developed efficient algorithm for mixed-motive tasks in multi-agent reinforcement learning.
For autonomous vehicles (AVs) to behave appropriately on roads populated by human-driven vehicles, they must be able to reason about the uncertain intentions and decisions of other drivers from rich perceptual information. Towards these capabilities, we present a probabilistic forecasting model of future interactions b…
New framework learns interaction rules from animal trajectories.
problem Challenges in extracting interaction rules from animal movement data.
method Augmented behavioral models with neural networks and theory-guided regularization.
result Improved performance over baselines and novel biological insights.
Extends driving model to control agent behavior in simulations.
problem Simulate realistic driving behavior for autonomous systems.
method Introduces Control-ITRA method to influence agent behavior through waypoint assignment and target speed modulation.
result Demonstrates controllable, infraction-free trajectories while preserving realism.
We present a method that learns to integrate temporal information, from a learned dynamics model, with ambiguous visual information, from a learned vision model, in the context of interacting agents. Our method is based on a graph-structured variational recurrent neural network (Graph-VRNN), which is trained end-to-end…
Generative ML learns optimal pursuit trajectories in pursuit-evasion games.
problem Optimizing Blue's pursuit trajectory to intercept Red in a game of pursuit-evasion.
method Applying generative machine learning to learn optimal action policies for Blue.
result Generative ML models can learn relevant representations for pursuit-evasion dynamics.
Estimates network structure and interaction rules from multiple agent trajectories.
problem Modeling multi-agent systems on networks from data.
method Jointly infers network topology and interaction kernels using non-convex optimization.
result ORALS estimator is consistent and asymptotically normal under coercivity conditions.
Develops a new model for controllable and realistic traffic simulation.
problem Lack of models that offer both controllability and realism in traffic simulation.
method Guided Conditional Diffusion (CTG) model using diffusion modeling and differentiable logic.
result Improves controllability-realism tradeoff over strong baselines.
This paper proposes a new algorithm for learning guidance rewards in RL.
problem Long-term temporal credit assignment in sparse or delayed reward environments.
method Surrogate RL objective with trajectory-space smoothing to learn guidance rewards.
result Guidance rewards can be learned without additional neural networks and have intuitive interpretation.
Autonomous driving is a multi-agent setting where the host vehicle must apply sophisticated negotiation skills with other road users when overtaking, giving way, merging, taking left and right turns and while pushing ahead in unstructured urban roadways. Since there are many possible scenarios, manually tackling all po…
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.
In this paper, we study the system identification problem for sparse linear time-invariant systems. We propose a sparsity promoting block-regularized estimator to identify the dynamics of the system with only a limited number of input-state data samples. We characterize the properties of this estimator under high-dimen…
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.
The paper formalizes and analyzes multi-agent Q-learning with value factorization.
problem Understanding and improving the convergence of multi-agent Q-learning with value factorization.
method Formalized a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning.
result Multi-agent Q-learning with linear value factorization can converge under certain conditions.
This paper extends off-policy reinforcement learning to the multi-agent case in which a set of networked agents communicating with their neighbors according to a time-varying graph collaboratively evaluates and improves a target policy while following a distinct behavior policy. To this end, the paper develops a multi-…
FACMAC combines deep policy gradients with factored critic for multi-agent reinforcement learning.
problem Cooperative multi-agent reinforcement learning in discrete and continuous action spaces.
method FACMAC uses a centralised but factored critic, combining per-agent utilities into a joint action-value function.
result FACMAC outperforms MADDPG and other baselines on multi-agent particle environments and StarCraft II tasks.
VectorNet predicts car behavior using vectorized HD maps and agent dynamics.
problem Predicting behavior in multi-agent systems with self-driving cars.
method VectorNet uses hierarchical graph neural networks on vectorized representations of HD maps and agent trajectories.
result VectorNet achieves comparable or better performance than state-of-the-art methods while using fewer parameters and less computational power.
This work benchmarks MARL algorithms in cooperative tasks.
problem Lack of evaluation tasks and criteria for comparing MARL algorithms.
method Systematic evaluation of three MARL algorithm classes in diverse cooperative tasks.
result Insights into the effectiveness of different learning approaches.
NeuroMAS treats multi-agent systems as neural networks for scalable, trainable coordination.
problem Designing multi-agent systems as hand-designed workflows is inefficient and inflexible.
method NeuroMAS treats multi-agent systems as a neural network architecture with reinforcement learning for scalable coordination.
result NeuroMAS improves significantly over multi-agent baselines and can be scaled progressively.
Parallelizes MCTS for continuous domains using leaf and root parallelization.
problem Solving challenging tasks in continuous domains using MCTS.
method Extends existing parallelization strategies to continuous domains, focusing on leaf and root parallelization.
result Proposes two final selection strategies for continuous states in root parallelization.
Study compares MAPF and MARL algorithms for warehouse automation.
problem Optimizing multi-agent pickup and delivery in warehouse settings.
method Compared conflict-based search (MAPF) and shared experience actor-critic (MARL).
result Comprehensive benchmarking of MAPF and MARL in a simulated warehouse environment.
MARL algorithm uses regularization to avoid explicit structures, improving performance.
problem Lack of effective reinforcement learning methods for multi-agent systems.
method MARQ uses regularization to promote structured exploration without explicit centralized structures.
result MARQ outperforms existing methods in multi-agent environments.
Improved exploration in cooperative multi-agent reinforcement learning.
problem Limited expressiveness of Gaussian policies in DecSPG hinders effective exploration.
method Proposes decentralized diffusion policy learning (DDPL) with denoising diffusion probabilistic models.
result Consistently improved performance on various MARL benchmarks.
New method combines value function decomposition and policy gradients for cooperative multi-agent reinforcement learning.
problem Challenges in cooperative multi-agent reinforcement learning, especially credit assignment and large action spaces.
method Decomposed Soft Actor-Critic (mSAC) method with Q network architecture, discrete probabilistic policy, and counterfactual advantage function.
result Significantly outperforms policy-based approach COMA and achieves competitive results with SOTA value-based approach Qmix.
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.
AutoDIME automates design of multi-agent environments for RL.
problem Designing multi-agent environments for reinforcement learning is challenging.
method Developed intrinsic teacher rewards for multi-agent settings and evaluated them in various tasks.
result Value disagreement was found to be most consistent and effective across tasks.
Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism…