Author manuscript, published in "Computer and Games, Beijing: China (2008)" Whole-History Rating: A Bayesian Rating System for Players of Time-Varying Strength

2008

Citations in the corpus

• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm (2017, methodology): “Figure 1 shows the performance of AlphaZero during self-play reinforcement learning, as a function of training steps, on an Elo scale (10).”
• Mastering Atari, Go, chess and shogi by planning with a learned model (2019, methodology): “[6] R.”
• High-Fidelity Generative Image Compression (2020, methodology): “We validated that the ordering is consistent with other methods for obtaining total orderings from pairwise comparisons that do not allow the computation of confidence intervals [37, 12].”
• Mastering the game of Go without human knowledge (2017, background): “Figure 3a shows the performance of AlphaGo Zero during self­play reinforcement learning, as a function of training time, on an Elo scale 25 .”
• A Generalised Method for Empirical Game Theoretic Analysis (2018, methodology): “Table 9: Meta-game payoff table generated for strategies s1 = [36, 35, 24, 3, 2], s2 = [37, 37, 21, 3, 2], and s3 = [35, 35, 26, 2, 2].”
• Temporal-difference search in computer Go (2012, unknown): “After all matches were complete, the results were analysed by the bayeselo program (Coulom 2008) to establish an Elo rating for every program.”
• A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT (2023, methodology): “The pairwise comparison relationships are later transferred to pointwise reward scalars, {𝑟1, 𝑟2, · · · , 𝑟3}, using an algorithm such as ELO [47].”
• Mastering Complex Control in MOBA Games with Deep Reinforcement Learning (2019, methodology): “We also use Elo rating (Coulom 2008) for comparing different versions of models, similar to that of AlphaGo (Silver et al.”