Essays about: "Candy Crush Saga"
Showing result 1 - 5 of 9 essays containing the words Candy Crush Saga.
-
1. Improving Generalization in Reinforcement Learningusing Skill-based Rewards
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Reinforcement Learning is a promising approach to develop intelligent agents that can help game developers in testing new content. However, applying it to a game with stochastic transitions like Candy Crush Friends Saga (CCFS) presents some challenges. READ MORE
-
2. How dark patterns affect desirability in Candy Crush Saga
University essay from Jönköping University/JTH, Datateknik och informatikAbstract : Dark game design patterns are features used by game creators to manipulate the player to make certain choices. These patterns can lead to unintentional player actions causing negative experiences. READ MORE
-
3. Scaling Reinforcement Learning Solutions For Game Playtesting
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Games are commonly used as playground for AI research, specifically in the field of Reinforcement Learning (RL). RL has shown promising results in developing intelligent agents to play a multitude of games. Previous work have explored how RL agents can be used in the process of playtesting in game development. READ MORE
-
4. DQN Tackling the Game of Candy Crush Friends Saga : A Reinforcement Learning Approach
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This degree project presents a reinforcement learning (RL) approach called deep Q-network (DQN) for learning how to play the game Candy Crush Friends Saga (CCFS). The DQN algorithm is implemented together with three extensions, which in 2015 resulted in a new state-of-the-art on the Atari 2600 domain. READ MORE
-
5. Using Reinforcement Learning for Games with Nondeterministic State Transitions
University essay from Linköpings universitet/Statistik och maskininlärningAbstract : Given the recent advances within a subfield of machine learning called reinforcement learning, several papers have shown that it is possible to create self-learning digital agents, agents that take actions and pursue strategies in complex environments without any prior knowledge. This thesis investigates the performance of the state-of-the-art reinforcement learning algorithm proximal policy optimization, when trained on a task with nondeterministic state transitions. READ MORE
