Action planning using learned and differentiable forward models of the world is a general approach which has a number of desirable properties, including improved sample complexity over modelfree RL methods, reuse of learned models across different tasks, and the ability to perform efficient gradient-based optimization in continuous action spaces. However, this approach does not apply straightfo...

Planning is a very important AI problem, and it is also a very time-consuming AI problem. To get an idea of how complex diierent planning problems are, it is useful to describe the computational complexity of diierent general planning problems. This complexity has been described for problems in which the result res(a; s) of applying an action a to a system in a state s is uniquely determined by...

AI planning research typically assumes that complete action models are given. On the other hand, popular approaches in reinforcement learning such as Q-learning completely eschew models and planning. Neither of these approaches is satisfactory to achieve robust human-level AI that includes planning and learning in rich structured domains. In this paper, we introduce the idea of planning with pa...

Analysing the structures of solution plans generated by AI Planning engines is helpful in improving the generative planning process, as well as shedding light in the study of its theoretical foundations. We investigate a specific property of solution plans, that we called linearity, which refers to a situation where each action achieves an atom (or atoms) for a directly following action, or ach...

This work presents an approach for the application of artificial intelligence planning techniques to the automatic generation of control sequences for manufacturing systems. These systems have some special features that must be considered in the planning process, but there are difficulties when the usual models of action are used to deal with these features. In this work, a specialized interval...

This work presents an approach for the application of artiicial intelligence planning techniques to the automatic generation of control sequences for manufacturing systems. These systems have some special features that must be considered in the planning process, but there are diiculties when the usual models of action are used to deal with these features. In this work, a specialized interval-ba...

Aiming at the former formalized methods of robot planning should give the environment state, can not obtain the new knowledge of the environment. In order to improve the reason ability for obtaining new knowledge of the environment state, the actions in the process of planning such as external action and sensing action are formalized. A formalized reasoning method—CPNI (Colored Petri Net for Pl...

Traditional AI planning systems have focussed on batch planning, where an entire plan for achieving a goal is generated. An alternative approach is to select only the next action, a technique that has been used in situated planners, and, more recently, has been eeectively applied to traditional AI planning domains. In this paper, we present an action selection framework sensitive to resource li...

Planning in large, partially observable domains is challenging, especially when a long-horizon lookahead is necessary to obtain a good policy. Traditional POMDP planners that plan a different potential action for each future observation can be prohibitively expensive when planning many steps ahead. An efficient solution for planning far into the future in fully observable domains is to use temp...