Dr Chris Child
Contact details
About
Overview
Chris has been the Associate Dean for Employability and Engagement since 2020, leading a number of technology based innovations in employability, such as virtual internships and client-based projects. He also instigated the Last Mile training programme at City, in partnership with Accenture, bridging the gap between university education and the corporate environment. He has been a games technology lecturer since 2005, and became course director for Computer Games in 2008. He launched City’s first apprenticeship (Data Science) in 2020 and is currently developing a full programme of apprenticeships based on existing MSc courses. Chris is also a researcher in the Department of Computer Science at City University, developing cutting edge game agent AI using techniques such as reinforcement learning, probabilistic planning, environment modelling and approximate dynamic programming.
Chris Child developed the Cricket Captain game series for PC, PlayStation and iPhone and has been working in the gaming industry for over 25 years. After several years at Empire and Logica CMG he now runs his own computer game company 'Childish Things Ltd' where he's involved in every stage of computer game production from game design, game programming, motion capture, writing manuals, right through to advertising and marketing.
Qualifications
- PhD Approximate Dynamic Programming with Parallel Stochastic Planning Operators, City, University London, United Kingdom, 2011
- PGDip Academic Practice, City, University London, United Kingdom, 2004
- MSc Cognitive Science, University of Birmingham, United Kingdom, 1994
- BSc Computer Science and Software Engineering, University of Birmingham, United Kingdom, 1993
Employment
- Senior Lecturer, City, University London, United Kingdom, April 2008 - present
- DIrector, Childish Things Ltd, April 2005 - present
- Visiting Lecturer, City, University London, United Kingdom, September 2003 - May 2008
- Designer, Manager & Programmer, Empire Interactive, July 1996 - October 2002
- Analyst Engineer, Logica plc, January 1995 - June 1996
- Analyst Engineer, Microsoft Development Lab, June - August 1993
Memberships of professional organisations
- Member, British Computing Society, April 2012 - present
- Member, IEEE, April 2012 - present
Research
Overview
My research is centred on the automated creation of intelligent agents for computer game environments, from the level of non-play characters in RPG or "god" games, to squad leaders and artificial opponents. The work is also applicable to a range of agent and robotics applications. My Ph.D. and publications focus on agents which build a stochastic rule based model from experience in an artificial environment which is either inherently random or random from the limited perspective of the agent's perception. This model is then used as the basis for a reinforcement learning algorithm (rule value reinforcement learning) which attaches value to each rule enabling the agent to pick an action in a given situation based on the values of rules with conditions matching the current state. Both the stochastic rule learning and rule value reinforcement learning algorithms are novel contributions. My future research interests include integrating agent research into commercial games and software engineering techniques for games.
Publications
Publications by category
Conference papers and proceedings (17)
- Child, C. and Ngo, L. DeeP-Mod: Deep Dynamic Programming Based Environment Modelling Using Feature Extraction. .doi:10.1007/978-981-95-1233-1_3
- Placek, H., Child, C. and Weyde, T. (2025). ORSA-T: Multi-View Object-Centric Scene Representation Learning with Slot Attention and Transformer. 2025 International Joint Conference on Neural Networks (IJCNN) 30 June-5 July.doi:10.1109/ijcnn64981.2025.11227165
- Child, C.H.T., Koluman, C. and Weyde, T. (2019). Modelling Emotion Based Reward Valuation with Computational Reinforcement Learning. Cogsci 2019 24-27 July, Montreal, Canada.
- Osudin, D., Child, C. and He, Y.-.H. Rendering Non-Euclidean Space in Real-Time Using Spherical and Hyperbolic Trigonometry. .doi:10.1007/978-3-030-22750-0_49
- Ollero, J. and Child, C. Performance Enhancement of Deep Reinforcement Learning Networks Using Feature Extraction. .doi:10.1007/978-3-319-92537-0_25
- Basaru, R.R., Child, C., Alonso, E. and Slabaugh, G. (2017). Hand Pose Estimation Using Deep Stereovision and Markov-Chain Monte Carlo. 2017 IEEE International Conference on Computer Vision Workshop (ICCVW) 22-29 October.doi:10.1109/iccvw.2017.76
- Basaru, R.R., Child, C., Alonso, E. and Slabaugh, G. (2017). Conditional Regressive Random Forest Stereo-Based Hand Depth Recovery. 2017 IEEE International Conference on Computer Vision Workshop (ICCVW) 22-29 October.doi:10.1109/iccvw.2017.78
- Basaru, R.R., Slabaugh, G.G., Child, C. and Alonso, E. (2016). HandyDepth: Example-based stereoscopic hand depth estimation using Eigen Leaf Node Features. 2016 International Conference on Systems, Signals and Image Processing (IWSSIP) 23-25 May.doi:10.1109/iwssip.2016.7502698
- Basaru, R.R., Child, C., Alonso, E. and Slabaugh, G. (2014). Quantized Census for Stereoscopic Image Matching. 2014 2nd International Conference on 3D Vision (3DV) 8-11 December.doi:10.1109/3dv.2014.83
- Child, C.H.T., Trusler, B.P., Dickinson, P. and Geril, P. (2014). Implementing Racing AI using Q-Learning and Steering Behaviours. GAMEON 2014 (15th annual European Conference on Simulation and AI in Computer Games) 9 January, University of Lincoln, Lincoln, UK.
- Child, C.H.T. and Dey, R. (2013). QL-BT: Enhancing Behaviour Tree Design and Implementation with Q-Learning. CIG 2013- IEEE Conference on Computational Intelligence and Games 11-13 August, Niagara Falls, Canada.
- Hadjiminas, N. and Child, C. (2012). Be The Controller: A Kinect Tool Kit for Video Game Control - Recognition of Human Motion Using Skeletal Relational Angles. The 5th International Conference on Computer Games and Allied Technology Bali, Indonesia.
- Child, C., Parkar, S., Mohamedally, D., Haddad, M. and Doroana, R. (2010). Development of a Virtual Laparoscopic Trainer using Accelerometer Augmented Tools to Assess Performance in Surgical training. 19th International Pediatric Endosurgery Group (IPEG) 8-12 June, Hawaii, USA..
- Child, C., Stathis, K. and Garcez, A.D. (2007). Learning to Act with RVRL Agents. 14th RCRA Workshop, Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion July-, Rome.
- Child, C. and Stathis, K. (2006). Rule Value Reinforcement Learning for Cognitive Agents. Fifth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS`06) 8-12 May, Hakodate, Hokkaido.doi:10.1145/1160633.1160773
- Child, C. and Stathis, K. SMART (Stochastic Model Acquisition with ReinforcemenT) learning agents: A preliminary report. .
- Child, C. and Stathis, K. The Apriori Stochastic Dependency Detection (ASDD) algorithm for learning Stochastic logic rules. .
Internet publication
- Child, C.H.T. and Georgeson, J.NPCs as People, Too: The Extreme AI Personality Engine. City, University of London.
Journal articles (4)
- Bailey, N., Child, C. and Weyde, T. (2026). Deep Learning Agents and the Emergence of Compositional Languages: Approaches, Inductive Biases and Measurement. Journal of Artificial Intelligence Research, 86. doi:10.1613/jair.1.17302
- Osudin, D., Denisova, A. and Child, C. (2025). Non-Euclidean Video Games: Exploring Player Perceptions and Experiences Inside Impossible Spaces. IEEE Transactions on Games, 17(1), pp. 115-124. doi:10.1109/tg.2024.3386816
- Aden, I., Child, C.H.T. and Reyes-Aldasoro, C.C. (2024). International Classification of Diseases Prediction from MIMIIC-III Clinical Text Using Pre-Trained ClinicalBERT and NLP Deep Learning Models Achieving State of the Art. Big Data and Cognitive Computing, 8(5), pp. 47-47. doi:10.3390/bdcc8050047
- Basaru, R.R., Child, C., Alonso, E. and Slabaugh, G. (2018). Data‐driven recovery of hand depth using CRRF on stereo images. IET Computer Vision, 12(5), pp. 666-678. doi:10.1049/iet-cvi.2017.0227
Report
- Child, C.H.T. (2012). Approximate Dynamic Programming with Parallel Stochastic Planning Operators. City University London.
Thesis/dissertation
- Child, C.H.T. Approximate Dynamic Programming with Parallel Stochastic Planning Operators. (PhD)
Professional activities
Online articles (3)
- Watching the rise and rise of eSports. (2015). City University London News http://www.city.ac.uk/news/2015/march/watching-the-rise-and-rise-of-esports
- Watching the rise and rise of eSports. (2015). City University London News https://www.city.ac.uk/news/2015/march/watching-the-rise-and-rise-of-esports
- Indie Cricket Developer Going All Out for Student Success. (2012). Edge Online http://www.edge-online.com/get-into-games/indie-cricket-developer-going-all-out-for-student-success/ An academic whose university development project became a long-running console cricket series is using his experience to inspire students and help them get a job in games. Dr Chris Child, who makes International Cricket Captain as owner of Childish Things, says the industry needs “hardcore programming specialists” rather than development all-rounders.
Other
- Cricket Captain 2014 released on PC, Mac, iPhone & Android. .