skip to main content

Explore Research Products in the NSF-PAR

Title: Multi-Agent Reinforcement Learning in Stochastic Networked Systems
We study multi-agent reinforcement learning (MARL) in a stochastic network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In general, scalability is a challenge in this setting because the size of the global state/action space can be exponential in the number of agents. Scalable algorithms are only known in cases where dependencies are static, fixed and local, e.g., between neighbors in a fixed, time-invariant underlying graph. In this work, we propose a Scalable Actor Critic framework that applies in settings where the dependencies can be non-local and stochastic, and provide a finite-time error bound that shows how the convergence rate depends on the speed of information spread in the network. Additionally, as a byproduct of our analysis, we obtain novel finite-time convergence results for a general stochastic approximation scheme and for temporal difference learning with state aggregation, which apply beyond the setting of MARL in networked systems.  more » « less
Award ID(s):
2105648
NSF-PAR ID:
10324693
Author(s) / Creator(s):
Date Published:
Journal Name:
Advances in Neural Information Processing Systems 34 (NeurIPS 2021)
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ( , Proceedings of the 40th International Conference on Machine Learning)
    Andreas Krause, Emma Brunskill (Ed.)
    Executing actions in a correlated manner is a common strategy for human coordination that often leads to better cooperation, which is also potentially beneficial for cooperative multi-agent reinforcement learning (MARL). However, the recent success of MARL relies heavily on the convenient paradigm of purely decentralized execution, where there is no action correlation among agents for scalability considerations. In this work, we introduce a Bayesian network to inaugurate correlations between agents’ action selections in their joint policy. Theoretically, we establish a theoretical justification for why action dependencies are beneficial by deriving the multi-agent policy gradient formula under such a Bayesian network joint policy and proving its global convergence to Nash equilibria under tabular softmax policy parameterization in cooperative Markov games. Further, by equipping existing MARL algorithms with a recent method of differentiable directed acyclic graphs (DAGs), we develop practical algorithms to learn the context-aware Bayesian network policies in scenarios with partial observability and various difficulty. We also dynamically decrease the sparsity of the learned DAG throughout the training process, which leads to weakly or even purely independent policies for decentralized execution. Empirical results on a range of MARL benchmarks show the benefits of our approach. 
    more » « less
  2. ; ; ( , 34th Annual Conference on Neural Information Processing Systems (NeurIPS), NeurIPS 2020)
    null (Ed.)
    We obtain global, non-asymptotic convergence guarantees for independent learning algorithms in competitive reinforcement learning settings with two agents (i.e., zero-sum stochastic games). We consider an episodic setting where in each episode, each player independently selects a policy and observes only their own actions and rewards, along with the state. We show that if both players run policy gradient methods in tandem, their policies will converge to a min-max equilibrium of the game, as long as their learning rates follow a two-timescale rule (which is necessary). To the best of our knowledge, this constitutes the first finite-sample convergence result for independent policy gradient methods in competitive RL; prior work has largely focused on centralized, coordinated procedures for equilibrium computation. 
    more » « less
  3. ( , The 13th International Conference on Intelligent Human Computer Interaction (IHCI-2021))
    The conventional machine learning (ML) and deep learning (DL) methods use large amount of data to construct desirable prediction models in a central fusion center for recognizing human activities. However, such model training encounters high communication costs and leads to privacy infringement. To address the issues of high communication overhead and privacy leakage, we employed a widely popular distributed ML technique called Federated Learning (FL) that generates a global model for predicting human activities by combining participated agents’ local knowledge. The state-of-the-art FL model fails to maintain acceptable accuracy when there is a large number of unreliable agents who can infuse false model, or, resource-constrained agents that fails to perform an assigned computational task within a given time window. We developed an FL model for predicting human activities by monitoring agent’s contributions towards model convergence and avoiding the unreliable and resource-constrained agents from training. We assign a score to each client when it joins in a network and the score is updated based on the agent’s activities during training. We consider three mobile robots as FL clients that are heterogeneous in terms of their resources such as processing capability, memory, bandwidth, battery-life and data volume. We consider heterogeneous mobile robots for understanding the effects of real-world FL setting in presence of resource-constrained agents. We consider an agent unreliable if it repeatedly gives slow response or infuses incorrect models during training. By disregarding the unreliable and weak agents, we carry-out the local training of the FL process on selected agents. If somehow, a weak agent is selected and started showing straggler issues, we leverage asynchronous FL mechanism that aggregate the local models whenever it receives a model update from the agents. Asynchronous FL eliminates the issue of waiting for a long time to receive model updates from the weak agents. To the end, we simulate how we can track the behavior of the agents through a reward-punishment scheme and present the influence of unreliable and resource-constrained agents in the FL process. We found that FL performs slightly worse than centralized models, if there is no unreliable and resource-constrained agent. However, as the number of malicious and straggler clients increases, our proposed model performs more effectively by identifying and avoiding those agents while recognizing human activities as compared to the stateof-the-art FL and ML approaches. 
    more » « less
  4. ; ; ; ( , International Conference on Machine Learning)
    Since reinforcement learning algorithms are notoriously data-intensive, the task of sampling observations from the environment is usually split across multiple agents. However, transferring these observations from the agents to a central location can be prohibitively expensive in terms of the communication cost, and it can also compromise the privacy of each agent’s local behavior policy. In this paper, we consider a federated reinforcement learning framework where multiple agents collaboratively learn a global model, without sharing their individual data and policies. Each agent maintains a local copy of the model and updates it using locally sampled data. Although having N agents enables the sampling of N times more data, it is not clear if it leads to proportional convergence speedup. We propose federated versions of on-policy TD, off-policy TD and Q-learning, and analyze their convergence. For all these algorithms, to the best of our knowledge, we are the first to consider Markovian noise and multiple local updates, and prove a linear convergence speedup with respect to the number of agents. To obtain these results, we show that federated TD and Q-learning are special cases of a general framework for federated stochastic approximation with Markovian noise, and we leverage this framework to provide a unified convergence analysis that applies to all the algorithms. 
    more » « less
  5. ; ; ; ( , International Conference on Machine Learning (ICML))
    Since reinforcement learning algorithms are notoriously data-intensive, the task of sampling observations from the environment is usually split across multiple agents. However, transferring these observations from the agents to a central location can be prohibitively expensive in terms of the communication cost, and it can also compromise the privacy of each agent’s local behavior policy. In this paper, we consider a federated reinforcement learning framework where multiple agents collaboratively learn a global model, without sharing their individual data and policies. Each agent maintains a local copy of the model and updates it using locally sampled data. Although having N agents enables the sampling of N times more data, it is not clear if it leads to proportional convergence speedup. We propose federated versions of on-policy TD, off-policy TD and Q-learning, and analyze their convergence. For all these algorithms, to the best of our knowledge, we are the first to consider Markovian noise and multiple local updates, and prove a linear convergence speedup with respect to the number of agents. To obtain these results, we show that federated TD and Q-learning are special cases of a general framework for federated stochastic approximation with Markovian noise, and we leverage this framework to provide a unified convergence analysis that applies to all the algorithms. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email