Unverified50% confidenceFactExact time
Empirical Game-Theoretic Analysis (EGTA) was systematically proposed by Michael Wellman and others at the University of Michigan; it constructs an empirical payoff matrix from match data collected over a limited strategy set in order to find Nash equilibria.
1
Sources
50%
Confidence
Long-term
Relevance
9/8/2026
First Seen
Sources
Related Entities
Related Claims
Unverified研究者已提出弹性权重巩固（EWC）、渐进式神经网络等缓解灾难性遗忘的方案，但在超大规模模型上的有效性仍是活跃研究方向63% similarVerifiedOpenAI o1 and DeepSeek-R1 achieve breakthroughs on complex benchmarks such as math competition problems by extending the chain of thought, which is essentially dynamically allocating more computational budget during the inference stage.62% similarUnverifiedTop-tier AI models have invested heavily in parameter scale, training data quality, and RLHF (Reinforcement Learning from Human Feedback) tuning, and therefore far outperform mid-to-low-end models on complex reasoning and code generation tasks61% similarVerifiedKnowledge distillation technology enables small models to extract a considerable proportion of capability from large models, undermining the validity of fixed compute thresholds as a proxy metric for capability.60% similarVerifiedMixture of Experts (MoE) models dynamically select a small number of experts to activate for each input token through a gating mechanism, thereby reducing the computational cost per inference while maintaining model capability.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/875613API
curl https://kongchang.com/api/v1/knowledge/claims/875613MCP
get_claim(id=875613)