Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints
We study the problem of multi-agent reinforcement learning (MARL) with adaptivity
constraints--a new problem motivated by real-world applications where deployments of new …
constraints--a new problem motivated by real-world applications where deployments of new …
Neighborhood curiosity-based exploration in multi-agent reinforcement learning
S Yang, Z He, J Li, H Shi, Q Ji… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Efficient exploration in cooperative multi-agent reinforcement learning is still tricky in
complex tasks. In this paper, we propose a novel multi-agent collaborative exploration …
complex tasks. In this paper, we propose a novel multi-agent collaborative exploration …
Intrinsic Motivation Exploration via Self-Supervised Prediction in Reinforcement Learning
Z Yang, H Du, Y Wu, Z Jiang… - 2024 6th International …, 2024 - ieeexplore.ieee.org
In many real-world scenarios, extrinsic rewards available to the agent are exceedingly
sparse. In such cases, curiosity can serve as an intrinsic reward signal, motivating the agent …
sparse. In such cases, curiosity can serve as an intrinsic reward signal, motivating the agent …