In this paper we proposed reinforcement learning algorithms with the generalized reward function. In our proposed method we use Q-learning and SARSA algorithms with generalised reward function to train the reinforcement learning agent. We evaluated the performance of our proposed algorithms on two real-time strategy games called BattleCity and S3. There are two main advantages of having such an...

The application of artificial intelligence (AI) to real-time strategy (RTS) games includes considerable challenges due to the very large state spaces and branching factors, limited decision times, and dynamic adversarial environments involved. To address these challenges, hierarchical task network (HTN) planning has been extended to develop a method denoted as adversarial HTN (AHTN), and this m...

The underlying goal of a competing agent in a discrete real-time strategy (RTS) game is to defeat an adversary. Strategic agents or participants must define an a priori plan to maneuver their resources in order to destroy the adversary and the adversary’s resources as well as secure physical regions of the environment. This a priori plan can be generated by leveraging collected historical knowl...

In this paper, we propose an automatic mechanism of Hierarchical Task Networks (HTNs) creation for solving the problem of real-time path planning in Real-Time Strategy (RTS) Games. HTNs are created using an abstraction of the game map. A real-time heuristic search approach called Learning Real-Time A* (LRTA) is applied to execute the primitive tasks of the HTNs. The main purpose of using a HTN ...

Gameplay in real-time strategy games seems somehow to be confined to a de facto standard where economical micromanagement is equally important as combat strategy, if not more important. To enable stronger combat-oriented gameplay without sacrificing other key aspects of the genre, we propose an automated system for scheduling unit training, which we believe may allow the exploration of new para...

Stackelberg games represent an important class of games in which one player, the leader, commits to a strategy and the remaining players, the followers, make their decision with knowledge of the leader’s commitment. Existing algorithms for Bayesian Stackelberg games find optimal solutions while modeling uncertainty over follower types with an a-priori probability distribution. Unfortunately, in...

Adversarial planning in complex decision domains, such as modern video games, has not yet received much attention from AI researchers. This thesis presents a planning framework (RTSplan) that uses simulation combined with Nash-equilibrium strategy approximation to choose the best policy from a given policy set. We apply this framework to an army deployment problem in an abstract real-time strat...

In this paper we study the computational complexity of computing an evolutionary stable strategy (ESS) in multi-player symmetric games. For two-player games, deciding existence ESS is complete for $$\mathrm {\Sigma }^\mathrm {p}_2$$ , second level polynomial time hierarchy. We show that a game closely connected to real Namely, problem hard class denote as $$\exists ^\mathrm {D}\cdot \forall \ma...

RTP (Real-Time Performers) is a software architecture capturing reflection mechanisms to support the dynamics of software real-time systems. Dynamics may comprise both behavioural and temporal issues. RTP relies on a strict separation of concerns between computational entities, alignment entities, and strategies activating both computational and alignments activities. This paper focuses on one ...

The importance of real-time character animation in computer games has increased considerably over the past decade. Due to advances in computer hardware and the achievement of great increases in computational speed, the demand for more realism in computer games is continuously growing. This paper will present and discuss various methods of 3D character animation and prospects of their real-time ...