Evaluation in Multi-Actor Policy Processes
نویسندگان
چکیده
منابع مشابه
Evaluation in multi-actor policy processes: accountability, learning and cooperation
Two main functions of evaluation are to enable accountability and collective learning. Both of these – and their combination – run into divers complications when applied in complex multi-actor policy processes. The article explores these complications and illustrates these with examples from the field of spatial policy. In doing so a third function of evaluation in such contexts is identified, ...
متن کاملExploring multi-actor value creation in IT service processes
Organizational information technology (IT) needs are served through increasingly complex configurations of people, technologies, organizations, and shared information. Ideally, an organizational IT service is valuable for both the providers and users of systems and solutions. However, mutually beneficial outcomes may be difficult to achieve within the configurations through which IT services ar...
متن کاملPerformance evaluation of single and multi-channel actor to actor communication for wireless sensor actor networks
The paper discusses two distributed actor to actor communication schemes (a single channel one and a multi-channel one) for wireless sensor actor networks (WSANs). The performance of these two schemes is evaluated through analysis and simulation. The simulation results show that the whole analysis is fairly accurate. It is further proven that the multichannel scheme has better performance than ...
متن کاملOff-Policy Actor-Critic
This paper presents the first actor-critic algorithm for off-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on actor-critic algorithms is limited to the on-policy setting and does not take advantage of the recent advances in offpolicy gradient temporal-difference learning....
متن کاملLinear Off-Policy Actor-Critic
This paper presents the first actor-critic algorithm for o↵-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on actor-critic algorithms is limited to the on-policy setting and does not take advantage of the recent advances in o↵policy gradient temporal-di↵erence learning. O↵...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Evaluation
سال: 2006
ISSN: 1356-3890,1461-7153
DOI: 10.1177/1356389006066972