{"total":13,"rows":[{"id":"2112.12228","title":"Direct Behavior Specification via Constrained Reinforcement Learning","created":"2021-12-22","cited_by_count":31,"area":null},{"id":"2307.11105","title":"Technical Challenges of Deploying Reinforcement Learning Agents for Game Testing in AAA Games","created":"2023-07-19","cited_by_count":12,"area":null},{"id":"2303.02160","title":"Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games","created":"2023-03-02","cited_by_count":11,"area":null},{"id":"2212.04401","title":"A Rubric for Human-like Agents and NeuroAI","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2312.02405","title":"BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks","created":"2023-12-05","cited_by_count":8,"area":null},{"id":"2202.10057","title":"CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectories","created":"2022-02-21","cited_by_count":6,"area":null},{"id":"2112.11731","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","created":"2021-12-22","cited_by_count":5,"area":null},{"id":"2309.15484","title":"Towards Human-Like RL: Taming Non-Naturalistic Behavior in Deep RL via Adaptive Behavioral Costs in 3D Games","created":"2023-09-27","cited_by_count":4,"area":null},{"id":"2511.15055","title":"Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2401.09491","title":"Memory, Space, and Planning: Multiscale Predictive Representations","created":"2024-01-16","cited_by_count":2,"area":null},{"id":"2506.03522","title":"Path Generation and Evaluation in Video Games: A Nonparametric Statistical Approach","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2203.05965","title":"Human-Like Navigation Behavior: A Statistical Evaluation Framework","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2607.07498","title":"Reward-Adaptive Iterative Discovery: A Case Study on Automated Game Testing for NHL26","created":"2026-07-08","cited_by_count":0,"area":null}],"next_cursor":null}