Certified policy smoothing for cooperative multi-agent reinforcement learning
Cooperative multi-agent reinforcement learning (c-MARL) is widely applied in safety-critical
scenarios, thus the analysis of robustness for c-MARL models is profoundly important …
scenarios, thus the analysis of robustness for c-MARL models is profoundly important …
Robustness testing for multi-agent reinforcement learning: State perturbations on critical agents
Multi-Agent Reinforcement Learning (MARL) has been widely applied in many fields such
as smart traffic and unmanned aerial vehicles. However, most MARL algorithms are …
as smart traffic and unmanned aerial vehicles. However, most MARL algorithms are …
[PDF][PDF] Marllib: A scalable multi-agent reinforcement learning library
Despite the fast development of multi-agent systems (MAS) and multi-agent reinforcement
learning (MARL) algorithms, there is a lack of unified evaluation platforms and commonly …
learning (MARL) algorithms, there is a lack of unified evaluation platforms and commonly …
Marllib: Extending rllib for multi-agent reinforcement learning
Despite the fast development of multi-agent reinforcement learning (MARL) methods, there
is a lack of commonly-acknowledged baseline implementation and evaluation platforms. As …
is a lack of commonly-acknowledged baseline implementation and evaluation platforms. As …
Towards comprehensive testing on the robustness of cooperative multi-agent reinforcement learning
While deep neural networks (DNNs) have strengthened the performance of cooperative
multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by …
multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by …
Cooperative and competitive biases for multi-agent reinforcement learning
Training a multi-agent reinforcement learning (MARL) algorithm is more challenging than
training a single-agent reinforcement learning algorithm, because the result of a multi-agent …
training a single-agent reinforcement learning algorithm, because the result of a multi-agent …
Model checking for adversarial multi-agent reinforcement learning with reactive defense methods
Cooperative multi-agent reinforcement learning (CMARL) enables agents to achieve a
common objective. However, the safety (aka robustness) of the CMARL agents operating in …
common objective. However, the safety (aka robustness) of the CMARL agents operating in …
Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning
Many complex multi-agent systems such as robot swarms control and autonomous vehicle
coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a …
coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a …
Shapley counterfactual credits for multi-agent reinforcement learning
Centralized Training with Decentralized Execution (CTDE) has been a popular paradigm in
cooperative Multi-Agent Reinforcement Learning (MARL) settings and is widely used in …
cooperative Multi-Agent Reinforcement Learning (MARL) settings and is widely used in …
Dealing with non-stationarity in marl via trust-region decomposition
Non-stationarity is one thorny issue in cooperative multi-agent reinforcement learning
(MARL). One of the reasons is the policy changes of agents during the learning process …
(MARL). One of the reasons is the policy changes of agents during the learning process …