In [15], the authors proposed a TD3-BC-PPO algorithm to address the problem of dynamic optimal design under adversarial real-time conditions, but it did not cover the MEC environment. Some works in [16], [17], [18], [19] indicated that in a system with multiple UAV supporting MEC,...
reinforcement-learningflaxcqlsingle-filejaxawaciqloffline-rloffline-reinforcement-learningd4rldecision-transformertd3bc UpdatedAug 15, 2024 Python Distributed Deep Learning framework based on Tensorflow2 reinforcement-learningamphigh-performanceppogailtd3parrallel-computingtensorflow2td3bccopg ...
deep-neural-networksreinforcement-learningdeep-learningdeep-reinforcement-learningddpgppoddpg-agenttd3ddpg-pytorchppo-pytorchtd3-pytorch UpdatedJan 5, 2025 Python Implementation of some deep RL algorithms reinforcement-learningdeep-reinforcement-learningpytorchdqna3cddpgactor-criticppotd3 ...