HyperAIHyperAI超神经
首页算力平台文档资讯论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

Atari Games On Atari 2600 Yars Revenge

评估指标

Score

评测结果

各个模型在此基准测试上的表现结果

Paper TitleRepository
Agent57998532.37Agent57: Outperforming the Atari Human Benchmark
R2D2995048.4Recurrent Experience Replay in Distributed Reinforcement Learning-
GDI-I3972000Generalized Data Distribution Iteration-
GDI-H3968090Generalized Data Distribution Iteration-
DNA564513DNA: Proximal Policy Optimization with a Dual Network Architecture
MuZero553311.46Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero (Res2 Adam)219838.09Online and Offline Reinforcement Learning by Planning with a Learned Model
DreamerV2156748Mastering Atari with Discrete World Models
Ape-X148594.8Distributed Prioritized Experience Replay
NoisyNet-Dueling86101Noisy Networks for Exploration
IMPALA (deep)84231.14IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
RUDDER60577RUDDER: Return Decomposition for Delayed Rewards
ASL DDQN29231.9Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
CGP28838.2Evolving simple programs for playing Atari games
IQN28379Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-126447Distributional Reinforcement Learning with Quantile Regression
Advantage Learning24240.03Increasing the Action Gap: New Operators for Reinforcement Learning
0 of 17 row(s) selected.
Atari Games On Atari 2600 Yars Revenge | SOTA | HyperAI超神经