=Paper=
{{Paper
|id=Vol-1928/paper3
|storemode=property
|title=A Vision on Analysing Approaches for Knowledge Representation and Reasoning Using Computer Games
|pdfUrl=https://ceur-ws.org/Vol-1928/paper3.pdf
|volume=Vol-1928
|authors=Christian Eichhorn,Vanessa Volz,Richard Niland,Tim Schendekehl
|dblpUrl=https://dblp.org/rec/conf/ki/EichhornVNS17
}}
==A Vision on Analysing Approaches for Knowledge Representation and Reasoning Using Computer Games==
https://ceur-ws.org/Vol-1928/paper3.pdf
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
A Vision on Analysing Approaches for
Knowledge Representation and Reasoning Using
Computer Games
Christian Eichhorn, Vanessa Volz, Richard Niland, and Tim Schendekehl
Faculty of Computer Science, TU Dortmund University, Dortmund, Germany
.@tu-dortmund.de
Abstract. Artificial intelligences (AIs) that interact with their environ-
ment are difficult to compare and evaluate as their formal properties
easily become incomparable due to fundamentally different knowledge
representations, reaction schemes, approaches and the general, very den-
dritic field of AI research. Nonetheless, AI approaches are regularly pro-
posed as solutions to complex “real world” problems in areas such as
self-driving cars or providing care for the elderly. Thus, the need for a
safe and controllable proving ground for different AI approaches with
scalable complexity emerges. Many researchers have argued that this
need can be fulfilled by using computer games as a testbed [17,16]. In
this paper, we propose a benchmark that specifically targets areas in
AI research that still pose great challenges in AI and human-computer
interaction research: the coordination of and cooperation among agents.
We thus introduce and present the platform game ZooOperation as
well as the corresponding competition involving this game at the KI 2017
conference, and illustrate how ZooOperation can serve as testbed for
the coordination and cooperation skills of various AI approaches. On
top of this, we discuss how this game, and computer games in general,
can be used in comparative AI research, e.g. in testing for robustness,
generalisability and human-computer interaction.
1 Introduction
Games have historically served as a testbed for artificial intelligence (cf. Alan
Turing’s chess-playing algorithm [17]). We, like many other researchers [16], ar-
gue that games continue to provide a great test environment for AI in general
and both knowledge representation and reasoning approaches in particular, es-
pecially if adapted according to the (intended) “real world” AI applications.
Evidently, the increasing complexity of game benchmarks (Go [14], Star-
Craft [10]) has resulted in the advent of various non-classical reasoning ap-
proaches using Monte-Carlo simulations and deep learning. This is because for
these games, classical AI approaches based on game theory such as alpha-beta-
pruning (and the underlying minimax-search) are at a severe disadvantage due
to the required (partial) enumeration of possible game states becoming compu-
tationally infeasible. The stochasticity of many games increases the state space
31
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
even further and additionally requires statistical considerations. Similarly, AI
approaches found in the area of knowledge representation and reasoning (KR)
that use semantic methods are sidelined in these benchmarks, as they do not
have the high reactiveness needed as the large number of possible states with
random transitions leads to excessively time-consuming computations.
Moreover, games provide an abstract, controllable and nearly arbitrarily com-
plex environment that can mimic the “real world” as closely as needed for a test
while keeping interfering influences at bay. For instance, in computer games and
other simulations, experiments can be conducted entirely without measurement
noise so that the real effects can be investigated free from falsifications, or a
specific, controlled amount of noise can be added deliberately to investigate how
well the approaches cope with it. Additionally, games can often be sped up to
enable repeated tests, as is needed, e.g., for evolutionary strategies. On top of
that, unlike simulations, games have the desirable property of offering an easy
approach to integrating humans into the loop by playing against or with AI
players. This fact has already successfully been used in various studies on hu-
man cognition [7,2]. Games also have motivational and immersive aspects which
facilitate both finding survey participants who make an honest effort, as well as
measuring their genuine reactions.
In the following, we argue that platform games (or platformers), that is,
games in the tradition of Donkey Kong (Nintendo, 1981), Impossible Mission
(Epyx, 1984), Prince of Persia (Brøderbund, 1989) and the most influential 1
Super Mario Bros. (Nintendo, 1985), which require the player to overcome a mul-
titude of obstacles (primarily by jumping between platforms, hence the name)
on their way to the goal, have additional merits as proving grounds for AI.
Advantages of using platformers as a testbed include, but are not limited to:
Scalability of Challenge Type The type of challenge can be varied easily,
e.g. by limiting the information on the environment through a change in
the agent’s visual range, by changing the “physical” stretch of the level, or
by restricting the time allowed for making decisions. As a result, both the
long-term planning capabilities and reactiveness of an AI agent can be tested
with a platformer.
Scalability of Challenge Difficulty Platform games provide a lot of different
parameters (e.g., different types and counts of obstacles) which can be used
to scale the difficulty of a level while keeping the core task unchanged.
Existence of Game Patterns It is not uncommon for levels in platformers
that certain sets of different obstacle types can be overcome using the same
techniques (e.g., jumping over a chasm, a body of water, or deadly spikes
covering the same horizontal space), so it is possible for two levels to differ
in their concrete obstacles while being identical in terms of the strategies
needed to reach the goal.
1
and, according to the Guinness World Records, best-selling video game
of all-time https://web.archive.org/web/20100224070604/http://gamers.
guinnessworldrecords.com/records/nintendo.aspx
32
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
Possibility of Multiple Solutions The layout of obstacles in a level usually
allows for more than one way to reach the goal. This gives room for evaluating
whether a strategy is successful without limiting its course of action more
than necessary, thus providing room for uncommon or “creative” solutions.
Generalisation Test By using different types of levels, it is possible to test
whether or not an approach is capable of generalising a valid solution (that
is, the solution to one level) to a similar, but not identical task (i.e. another
level following the same rules but differing in terms of design).
Following this introduction to the paper and the topic in general, we present
the game ZooOperation in the subsequent Section 2 by consecutively intro-
ducing the game itself in Section 2.1, existing controllers for the avatars in Sec-
tion 2.2 and finally the corresponding ZooOperation competition in the scope
of the KI 2017 conference in Section 2.3. This is followed by a discussion of how
computer games may support research in the various areas of artificial intelli-
gence (Section 3), where we describe further questions and characteristics that
are suitable for the analysis of KR approaches based on their empirical per-
formance in the game. We afterwards conclude the article in Section 4 with a
summary and our suggestions on future applications of ZooOperation.
2 ZooOperation
The game ZooOperation is a cooperative platform game inspired by the
game Geometry Friends [12] and was created as a student project at TU Dort-
mund University [3]. Unlike this and other cooperative games such as RoboCup
(Simulation League) 2 , ZooOperation challenges planning, coordination and
collaboration almost exclusively through removing the additional complexity of
extensive physics simulations. Additionally, with ZooOperation, we challenge
the AIs with avatars that each have different but closely defined abilities that
have to be coordinated to reach the goal. This differs from other cooperative
challenges as, for instance, the Robo Cup Simulation League3 or Neuro-Evolving
Robotic Operatives4 , where a swarm of avatars with more or less the same set
of skills has to reach a common goal.
2.1 Game description
In ZooOperation, up to five agents each take control over one of a fixed set of
avatars where every avatar has unique capabilities; Figure 1 gives an overview
over the avatars in the game. To finish a level in this game, all present avatars
must reach the designated final destination in the level; Figure 3a shows an
example of a level in this game. In order to reach this goal, the avatars have
to cross the level while circumventing various obstacles (shown in Figure 2) on
the way. These may be harmless obstacles that just obstruct the movement of
2
http://www.robocup2017.org
3
http://wiki.robocup.org/Soccer_Simulation_League
4
http://nn.cs.utexas.edu/nero/
33
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
Crocodile, capable of Mouse, can change its di-
climbing harmless game mensions, but not its surface
elements. area.
Tiger, can run quicker and Piglet, can serve as a tram-
jump further than any other poline, giving other avatars
avatar. a wider jump range.
Elephant, can swim and
carry other avatars over bod-
ies of water.
Fig. 1: Avatars in the game ZooOperation [3].
Ground, walkable ground
Wall, for topological design
for topological design of
of level.
level, sometimes grassy.
Box, movable and walkable Coil spring, catapults an
obstacle. avatar upwards.
Goal, must be reached by all
Moving Platform, a walk-
present avatars to finish the
able platform that moves.
level.
Spikes, dangerous game el-
Water, dangerous element
ement, fixed on ground or
for every non-swimming
ceiling. May fall down if an
avatar.
avatar walks underneath.
Fig. 2: Game elements in the game ZooOperation [3].
34
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
(a) Cooperative level: Tiger needs to clear the way of falling spikes for Elephant
to be able to walk to the goal.
(b) Cooperative task: Ele- (c) Complex obstacle: Mouse lifts Tiger high
phant carries Tiger over a enough for it to be able to jump over the wall,
body of water too wide to then has to change its shape to fit through the
jump over. gap.
Fig. 3: Different obstacles in ZooOperation to be overcome through coopera-
tion [3].
certain avatars (for instance, being too high to jump over or too narrow to crawl
underneath), or deadly obstacles like fixed or falling spikes, deep chasms, or
bodies of water. In many cases, it is possible to overcome these obstacles using
different strategies for different avatars. For instance, Tiger can jump over a body
of water, whereas Elephant swims through it, but the other avatars require a
different, cooperative strategy because they can neither jump far enough nor
swim. A possible solution to this specific problem is for the avatar to be carried
across the water by Elephant (see Figure 3b). Other cooperative obstacles include
pathways that have to be cleared by a smaller avatar before a larger one can fit
through (Figure 3a) or complex obstacles where special capabilities of different
avatars have to be combined to overcome the obstacle (Figure 3c).
To test AI controllers, the game provides a TCP/IP interface that sends the
game state to every bound AI controller and allows the AIs to control the avatars
and send user-defined messages to be read by all other AIs (“Blackboard”). The
controls provided to interact with the game are the same ones a human player
might use, that is, the AI can send keystrokes for up, down, left, right, special
(for special skills of the avatar, if applicable). Therefore, it is not necessary to
35
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
specialise an AI approach for or deeply integrate the approach into the game,
but it instead suffices to provide the aforementioned TCP/IP interface that acts
as a bilateral translator. This interface needs to (1) translate the game state into
a form the AI can understand and (2) translate the designated action of the AI
into keystrokes to be sent to the game.
2.2 Automated ZooOperation Controllers
As described above, the game ZooOperation has been developed specifically
for testing different AIs. In the project it was developed for, it has already been
used to assess and train different controller types and strategies. To illustrate how
diverse approaches and controllers for solving levels in ZooOperation may be,
we highlight a selection of three strategies already developed and applied to the
game; see the project report [3] for a complete overview and detailed description
of all strategies developed.
Graph Approach: The graph approach construes a level as a directed graph,
where every (physically) coherent traversable area with identical headroom is
interpreted as a vertex. An edge is added for every movement in the game that
allows the individual avatar to change its position from one of the vertices to
another. This relocation can be achieved e.g. by walking, parabolic jumping
or falling (to a lower vertex). A vertex in the graph is reachable (in a graph-
theoretic sense), if and only if it is also reachable in the game, that is, there is a
combination of movements that allows the player to manoeuvre the avatar from
the starting vertex to the final vertex. Using this approach, a level can be solved
by a standard algorithm for finding (shortest) paths in graphs given that the
level is solvable without cooperation.
Dynamic Jump: Sometimes, parabolic jumping does not give all possible targets
an avatar can reach, as there may be obstacles in the way or the ceiling is low.
Using the techniques of dynamic programming, this approach calculates all posi-
tions that are reachable from a fixed starting position via a jump or a fall. During
this, it populates a table with reachability information for every potential future
position of the avatar up to a predefined time limit. It then goes backwards from
a destination to find a possible path and the corresponding commands. This has
also been used to generate extra edges for the graph approach described above.
Figure 4a illustrates the result of one such calculation, that is, the traversals and
endpoints an avatar can reach from its actual position using a single dynamic
jump.
Motif Search: The prior two approaches use knowledge only in terms of the
properties of the characters and the underlying game’s physics (how far and
high can a character jump, how fast can it run, . . . ).
Motif search instead stores obstacles and corresponding solutions in the form
of so-called motifs. A motif is a tuple of an abstract representation of the obstacle,
the sequence of keystrokes that yield a valid solution (also called an action
36
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
(a) Black lines indicate movements (b) Example motif with start- (circle) and
Tiger can make with a dynamic jump endpoint (double circle), walkable tiles
from its actual position (endpoints (gray) and traversal (dashed).
of lines pointing to Tiger’s centre of
gravity after the jump).
Fig. 4: Illustrations of approaches to solving ZooOperation levels [3].
sequence), and the area around the obstacle that is traversed when performing
the action sequence. The abstract representation takes the form of a matrix
of tiles which encode whether or not a tile is safe to walk through, stand on,
etc., and also stores the start and end position of the avatar performing the
sequence. These motifs may then be mapped to concrete areas of a level using a
distance function on the abstract tiles in the motif and the actual tiles in the level,
allowing, for instance, an agent to use the same strategy used to jump over a pit of
“dangerous” tiles regardless of whether these tiles are filled with water, spikes or
other dangerous elements. Figure 4b is an example of an obstacle’s representation
by a motif. These motifs can, for instance, be recorded from playthroughs of
human or AI players, generated by a machine learning approach, or designed by
hand.
2.3 ZooOperation Competition at KI 2017
ZooOperation will be used in a competition at KI 2017 intended to measure
the path planning, coordination and puzzle solving capabilities of submitted AI
agents. Participants can upload their AI controllers which will then face two
types of levels:
– small levels with a single obstacle that may or may not require cooperation
to overcome, and
– regular levels that combine multiple challenges, an example of which is de-
picted in Figure 5.
The submissions are ranked according to the number of regular levels they fin-
ished. In case of a draw, we use the number of small levels finished as a secondary
ranking criterion. Any remaining ties will be broken using the time needed to
finish the level, measured in terms of the number of game ticks elapsed. Apart
from the tertiary ranking criterion, the controllers are not required to make quick
37
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
Fig. 5: A regular level from the ZooOperation competition: In order to finish
the level, Tiger has to carry Elephant so it can master the stairs. Then Elephant
must carry Tiger so it can cross the big body of water. During this “boat trip”,
Tiger must jump on and over the obstacles so it is neither pushed in the water
nor killed by the spikes.
real-time decisions, but instead have a maximum of eight minutes per level to
solve it. With only a loose time restriction, complete and perfect information
and a deterministic game engine, this competition (in contrast to other compe-
titions such as GVGAI5 and Geometry Friends6 ) stresses the cooperation and
problem solving aspects of (cooperative) platformers. Thus, it is possible to in-
clude multiple approaches which may differ in their reaction speed, and judge
them by their general capability of solving a level in the game rather than the
time needed to calculate a solution.
At the same time, the continuous environment provides a challenge differ-
ent from grid-based problems such as, for instance, the Wumpus World [13]. In
addition to the selected approaches from [3] used as illustrating examples in Sec-
tion 2.2, we encourage submissions using diverse strategies and controllers, the
possibility of which is ensured by the TCP/IP interface (Section 2.1).
Technically, the competition backend is realised via a web server that provides
a user account system backed by a relational database. Here, users may upload
AIs to the server where they will be enqueued and tested within a sandbox
container using the Docker framework. The test results are then extracted and
stored in the database to be displayed as leaderboards. The Docker framework
was chosen for this task due to its high scalability and automatic load balancing
between containers, allowing for a dynamic reallocation of resources depending
on how intensely users strain the system through frequent uploads and tests.
On top of that, Docker containers do not expose the underlying server system,
impeding malicious action such as a modification of the competition framework.
3 Discussion
The competition at KI 2017 is of course only one of the possible competition
setups and scoring schemes that can be based on the ZooOperation software.
Since the setup directly characterises the challenges the game provides and steers
the focus of the competition, different setups can be employed in order to in-
vestigate other aspects of AI. In the following, we list and discuss the different
5
General Video Game Playing Competition, http://gvgai.net
6
Cooperative physics puzzles, http://gaips.inesc-id.pt/geometryfriends/
38
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
experimentation scenarios we envision in context of AI research using the Zoo-
Operation software.
Multi Agent Systems: Cooperation generally requires communication among
agents. Additionally, to reason whether avatar B is capable of helping avatar
A to overcome an obstacle, the controller of A needs a model of B as well.
In order to focus on this aspect, the software can restrict information on
other agents so that communication between agents is enforced, controlled,
or restricted.
Knowledge Representation and Reasoning: The motif approach already
uses abstract knowledge to represent partial solutions. Thus, it seems rea-
sonable to examine whether an even more abstract representation, such as a
hierarchical knowledge base [1] or a representation using defeasible (condi-
tional) rules to form a conditional knowledge base with respective semantics
(see, e.g., [4,15,6,9]) yields satisfactory results, too. In order to specifically
analyse the knowledge representation aspects, one could restrict the informa-
tion passed to the agent accordingly, for example by passing all information
through an interface that prohibits or redacts specific information.
AI Generalisability: Motif search is only one of the possible approaches that
use abstraction in order to generalise from previously learned behaviour. In
recent years, the computational intelligence in games community has put
considerable effort into finding generalisable AI approaches [11]. The games,
however, tend to be extremely different and do not produce observable pat-
terns across different AIs [8]. Using a similarity measure on levels, the need
for generalisability could be scalarised in an experiment scenario in order to
identify issues where general game AI breaks.
AI Robustness In order to investigate approaches based on uncertain reason-
ing and belief revision, the information provided to AI players could be
limited or otherwise modified in order to create scenarios in which employ-
ing the respective techniques becomes inevitable. For example, the physics
of the game could be be unknown to the AIs (as is the case in the Angry
Birds AI Competition7 for instance) or be subject to undisclosed changes
(e.g. by randomly changing gravity). Another possible scenario is one where
the characters in the level are controlled by AIs that are unfamiliar with one
another.
Measuring Game Characteristics: Measuring game characteristics such as
difficulty and required strategy depth are open issues of interest within the
computational intelligence in games community [8,2]. We plan to extend
future work in this regard by investigating measures that can identify levels
of the same difficulty class based on empirical results of different AI agents
playing ZooOperation.
Involving Human Players: As artificial ZooOperation controllers and hu-
man players steer the characters in the same way, it is possible to include
human players in the experiments. Possible scenarios include the compar-
ison of behaviour patterns of AI and human players as well as identifying
7
https://aibirds.org/angry-birds-ai-competition.html
39
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
explanatory components for black-box agents by asking human players that
have gained expertise through repeated games. Furthermore, the challenge
could be extended to include human-computer-interaction by building mixed
AI and human teams that need to communicate and collaborate (cf. [5]).
4 Conclusion
In this paper, we made a case for using computer games to test and compare
approaches from artificial intelligence and, specifically, approaches from knowl-
edge representation and reasoning. We presented the game ZooOperation and
illustrated how platform games in general, and this game in particular, can serve
as a proving ground to investigate a variety of questions. Additionally, we pro-
vided a description of the ZooOperation competition at KI 2017 as an example
for investigating the path planning, coordination and puzzle solving capabilities
of AI agents along with an overview of suitable solutions. We already invited
other researchers of AI to use ZooOperation as test bed for their approaches
and / or to compete with each other in the ZooOperation competition. We
discussed how the presented game, and computer games in general, can be used
to investigate and rank different approaches to AI in terms of further properties,
be it communication, knowledge representation and reasoning, or robustness and
generalisability of AIs. This underpins our general claim that computer games
provide a viable proving ground for judging and comparing AI-approaches in
addition to their formal properties.
This, of course, was only the first step, and future work can be broken into
two major parts: First, applying established AI approaches to the task of solving
platform games like ZooOperation as a simulation of tasks in complex envi-
ronments, and comparing them with each other based on their performance in
these simulations. Second, as indicated in the discussion, this general framework
can help in improving interactions between human users and automated sys-
tems through researching, for example, general notions of difficulty of (scalably)
complex tasks (as seen in platform games), or the performance and results of
mixing human and artificial players (involving humans as sparring partners or
as members of mixed teams).
Acknowledgements
We thank the anonymous reviewers for their valuable hints that helped us im-
prove the paper. This work was supported by DFG-Grant KI1413/5-1 as part of
the priority program “New Frameworks of Rationality” (SPP 1516) and DFG re-
search unit FOR 1513 on “Hybrid Reasoning for Intelligent Systems” to Gabriele
Kern-Isberner. Christian Eichhorn is supported by Grant KI1413/5-1, Richard
Niland is supported by FOR 1513.
40
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
References
1. Apeldoorn, D., Kern-Isberner, G.: When Should Learning Agents Switch to Ex-
plicit Knowledge? In: Benzmüller, C., Sutcliffe, G., Rojas, R. (eds.) GCAI 2016.
2nd Global Conference on Artificial Intelligence. EPiC Series in Computing, vol. 41,
pp. 174–186. EasyChair Publications (2016)
2. Apeldoorn, D., Volz, V.: Measuring Strategic Depth in Games Using Hierarchical
Knowledge Bases. In: Computational Intelligence in Games Conference (CIG). pp.
9–16. IEEE Press, New York, NY, USA (2017)
3. Buttkus, M., Fecke, M., Gärtner, D., Junge, J., Majchrzak, K., Nehrke, A., Schen-
dekehl, T., Schlüter, C., Shao, X.: ZooOperation: Spielende kooperierende Agenten.
Projektgruppenbericht der PG 596, Faculty of Computer Science, TU Dortmund
University, Dortmund, DE (2016), (in German)
4. Dubois, D., Prade, H.: Possibility Theory and Its Applications: Where Do We
Stand? In: Kacprzyk, J., Pedrycz, W. (eds.) Springer Handbook of Computational
Intelligence, pp. 31–60. Springer Berlin Heidelberg, Berlin, DE (2015)
5. Eger, M., Martens, C., Córdoba, M.A.: An Intentional AI for Hanabi. In: CIG’2017
- IEEE Conference on Computational Intelligence and Games. pp. 68–75. IEEE
CIG, IEEE Computer Society, New York, NY, USA (2017)
6. Eichhorn, C., Kern-Isberner, G.: Qualitative and Semi-Quantitative Inductive Rea-
soning with Conditionals. KI – Künstliche Intelligenz 29(3), 279–289 (2015)
7. Holmgård, C., Togelius, J., Henriksen, L.: Computational Intelligence and Cog-
nitive Performance Assessment Games. In: Computational Intelligence in Games
Conference (CIG). pp. 485–492. IEEE Press, Santorini, Greece (2016)
8. Horn, H., Volz, V., Perez-Liebana, D., Preuss, M.: MCTS/EA hybrid GVGAI
players and game difficulty estimation. In: Computational Intelligence in Games
Conference (CIG). pp. 278–285. IEEE Press, Santorini, Greece (2016)
9. Kern-Isberner, G.: Conditionals in Nonmonotonic Reasoning and Belief Revision
– Considering Conditionals as Agents. No. 2087 in Lecture Notes in Computer
Science, Springer Science+Business Media, Berlin, DE (2001)
10. Ontanon, S., Synnaeve, G., Uriarte, A., Richoux, F., Churchill, D., Preuss, M.: A
Survey of Real-Time Strategy Game AI Research and Competition in StarCraft.
IEEE Transactions on Computational Intelligence and AI in Games 5(4), 293–311
(2013)
11. Perez, D., Samothrakis, S., Togelius, J., Schaul, T., Lucas, S.M., Couëtoux, A., Lee,
J., Lim, C.U., Thompson, T.: The 2014 General Video Game Playing Competition.
IEEE Transactions on Computational Intelligence and AI in Games 8(3), 229–243
(2015)
12. Prada, R., Lopes, P., Catarino, J., Quitério, J., Melo, F.S.: The Geometry Friends
Game AI Competition. In: CIG’2015 - IEEE Conference on Computational In-
telligence and Games. pp. 431–438. IEEE CIG, IEEE Computer Society, Tainan,
Taiwan (2015)
13. Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall
series in artificial intelligence, Prentice Hall (2010)
14. Silver, D., Huang, A., Maddison, C.J., Guez, A., Sifre, L., van den Driessche, G.,
Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S.,
Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M.,
Kavukcuoglu, K., Graepel, T., Hassabis, D.: Mastering the game of Go with deep
neural networks and tree search. Nature 529(7587), 484–489 (2016)
41
Proceedings of the KI 2017 Workshop on Formal and Cognitive Reasoning
15. Spohn, W.: The Laws of Belief: Ranking Theory and Its Philosophical Applications.
Oxford University Press, Oxford, UK (2012)
16. Togelius, J.: AI Researchers, Video Games Are Your Friends! In: Merelo, J.J.,
Rosa, A., Cadenas, J.M., Correia, A.D., Madani, K., Ruano, A., Filipe, J. (eds.)
7th International Joint Conference on Computational Intelligence (IJCCI 2015).
pp. 3–18. Springer International Publishing, Cham, CH, Lisbon, Portugal (2016)
17. Turing, A., Bates, M.A., Bowden, B., Strachey, C.: Digital computers applied to
games. In: Bowden, B. (ed.) Faster than Thought, chap. 25, pp. 286–310. Sir Isaac
Pitman & Sons, Ltd., London, UK (1953)
42