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

Command Palette

Search for a command to run...

Atari Games On Atari 2600 Space Invaders

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
GDI-H3154380Generalized Data Distribution Iteration-
GDI-H3(200M frames)154380Generalized Data Distribution Iteration-
GDI-I3140460GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
GDI-I3140460Generalized Data Distribution Iteration-
MuZero74335.30Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Ape-X54681Distributed Prioritized Experience Replay
Agent5748680.86Agent57: Outperforming the Atari Human Benchmark
FQF46498.3Fully Parameterized Quantile Function for Distributional Reinforcement Learning
IMPALA (deep)43595.78IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
R2D243223.4Recurrent Experience Replay in Distributed Reinforcement Learning-
IQN28888Implicit Quantile Networks for Distributional Reinforcement Learning
A3C LSTM hs23846.0Asynchronous Methods for Deep Reinforcement Learning
ASL DDQN21602Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
QR-DQN-120972Distributional Reinforcement Learning with Quantile Regression
A3C FF hs15730.5Asynchronous Methods for Deep Reinforcement Learning
Prior+Duel noop15311.5Dueling Network Architectures for Deep Reinforcement Learning
Rainbow12629.0Rainbow: Combining Improvements in Deep Reinforcement Learning
Prior+Duel hs8978.0Deep Reinforcement Learning with Double Q-learning
Duel noop6427.3Dueling Network Architectures for Deep Reinforcement Learning
Duel hs5993.1Dueling Network Architectures for Deep Reinforcement Learning
0 of 55 row(s) selected.
Atari Games On Atari 2600 Space Invaders | SOTA | HyperAI超神经