在深度强化学习方法中,针对内在好奇心模块(intrinsic curiosity model,ICM)指导智能体在稀疏奖励环境中获得未知策略学习的机会,但好奇心奖励是一个状态差异值,会使智能体过度关注于对新状态的探索,进而出现盲目探索的问题,提出了一种...在深度强化学习方法中,针对内在好奇心模块(intrinsic curiosity model,ICM)指导智能体在稀疏奖励环境中获得未知策略学习的机会,但好奇心奖励是一个状态差异值,会使智能体过度关注于对新状态的探索,进而出现盲目探索的问题,提出了一种基于知识蒸馏的内在好奇心改进算法(intrinsic curiosity model algorithm based on knowledge distillation,KD-ICM)。首先,该算法引入知识蒸馏的方法,使智能体在较短的时间内获得更丰富的环境信息和策略知识,加速学习过程;其次,通过预训练教师神经网络模型去引导前向网络,得到更高精度和性能的前向网络模型,减少智能体的盲目探索。在Unity仿真平台上设计了两个不同的仿真实验进行对比,实验表明,在复杂仿真任务环境中,KD-ICM算法的平均奖励比ICM提升了136%,最优动作概率比ICM提升了13.47%,提升智能体探索性能的同时能提高探索的质量,验证了算法的可行性。展开更多
针对航天器与非合作目标追逃博弈的生存型微分对策拦截问题,基于强化学习研究了追逃博弈策略,提出了自适应增强随机搜索(adaptive-augmented random search,A-ARS)算法。针对序贯决策的稀疏奖励难题,设计了基于策略参数空间扰动的探索方...针对航天器与非合作目标追逃博弈的生存型微分对策拦截问题,基于强化学习研究了追逃博弈策略,提出了自适应增强随机搜索(adaptive-augmented random search,A-ARS)算法。针对序贯决策的稀疏奖励难题,设计了基于策略参数空间扰动的探索方法,加快策略收敛速度;针对可能过早陷入局部最优问题设计了新颖度函数并引导策略更新,可提升数据利用效率;通过数值仿真验证并与增强随机搜索(augmented random search,ARS)、近端策略优化算法(proximal policy optimization,PPO)以及深度确定性策略梯度下降算法(deep deterministic policy gradient,DDPG)进行对比,验证了此方法的有效性和先进性。展开更多
The deep deterministic policy gradient(DDPG)algo-rithm is an off-policy method that combines two mainstream reinforcement learning methods based on value iteration and policy iteration.Using the DDPG algorithm,agents ...The deep deterministic policy gradient(DDPG)algo-rithm is an off-policy method that combines two mainstream reinforcement learning methods based on value iteration and policy iteration.Using the DDPG algorithm,agents can explore and summarize the environment to achieve autonomous deci-sions in the continuous state space and action space.In this paper,a cooperative defense with DDPG via swarms of unmanned aerial vehicle(UAV)is developed and validated,which has shown promising practical value in the effect of defending.We solve the sparse rewards problem of reinforcement learning pair in a long-term task by building the reward function of UAV swarms and optimizing the learning process of artificial neural network based on the DDPG algorithm to reduce the vibration in the learning process.The experimental results show that the DDPG algorithm can guide the UAVs swarm to perform the defense task efficiently,meeting the requirements of a UAV swarm for non-centralization,autonomy,and promoting the intelligent development of UAVs swarm as well as the decision-making process.展开更多
文摘在深度强化学习方法中,针对内在好奇心模块(intrinsic curiosity model,ICM)指导智能体在稀疏奖励环境中获得未知策略学习的机会,但好奇心奖励是一个状态差异值,会使智能体过度关注于对新状态的探索,进而出现盲目探索的问题,提出了一种基于知识蒸馏的内在好奇心改进算法(intrinsic curiosity model algorithm based on knowledge distillation,KD-ICM)。首先,该算法引入知识蒸馏的方法,使智能体在较短的时间内获得更丰富的环境信息和策略知识,加速学习过程;其次,通过预训练教师神经网络模型去引导前向网络,得到更高精度和性能的前向网络模型,减少智能体的盲目探索。在Unity仿真平台上设计了两个不同的仿真实验进行对比,实验表明,在复杂仿真任务环境中,KD-ICM算法的平均奖励比ICM提升了136%,最优动作概率比ICM提升了13.47%,提升智能体探索性能的同时能提高探索的质量,验证了算法的可行性。
文摘针对航天器与非合作目标追逃博弈的生存型微分对策拦截问题,基于强化学习研究了追逃博弈策略,提出了自适应增强随机搜索(adaptive-augmented random search,A-ARS)算法。针对序贯决策的稀疏奖励难题,设计了基于策略参数空间扰动的探索方法,加快策略收敛速度;针对可能过早陷入局部最优问题设计了新颖度函数并引导策略更新,可提升数据利用效率;通过数值仿真验证并与增强随机搜索(augmented random search,ARS)、近端策略优化算法(proximal policy optimization,PPO)以及深度确定性策略梯度下降算法(deep deterministic policy gradient,DDPG)进行对比,验证了此方法的有效性和先进性。
基金supported by the Key Research and Development Program of Shaanxi(2022GY-089)the Natural Science Basic Research Program of Shaanxi(2022JQ-593).
文摘The deep deterministic policy gradient(DDPG)algo-rithm is an off-policy method that combines two mainstream reinforcement learning methods based on value iteration and policy iteration.Using the DDPG algorithm,agents can explore and summarize the environment to achieve autonomous deci-sions in the continuous state space and action space.In this paper,a cooperative defense with DDPG via swarms of unmanned aerial vehicle(UAV)is developed and validated,which has shown promising practical value in the effect of defending.We solve the sparse rewards problem of reinforcement learning pair in a long-term task by building the reward function of UAV swarms and optimizing the learning process of artificial neural network based on the DDPG algorithm to reduce the vibration in the learning process.The experimental results show that the DDPG algorithm can guide the UAVs swarm to perform the defense task efficiently,meeting the requirements of a UAV swarm for non-centralization,autonomy,and promoting the intelligent development of UAVs swarm as well as the decision-making process.
