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 Crazy Climber

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
Agent57565909.85Agent57: Outperforming the Atari Human Benchmark
MuZero458315.40Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D2366690.7Recurrent Experience Replay in Distributed Reinforcement Learning-
Ape-X320426Distributed Prioritized Experience Replay
GDI-H3241170Generalized Data Distribution Iteration-
Reactor 500M236422.0The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning-
FQF223470.6Fully Parameterized Quantile Function for Distributional Reinforcement Learning
GDI-I3201000GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
GDI-I3201000Generalized Data Distribution Iteration-
C51 noop179877.0A Distributional Perspective on Reinforcement Learning
IQN179082Implicit Quantile Networks for Distributional Reinforcement Learning
NoisyNet-Dueling171171Noisy Networks for Exploration
ASL DDQN166019Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior+Duel noop162224.0Dueling Network Architectures for Deep Reinforcement Learning
DreamerV2161839Mastering Atari with Discrete World Models
QR-DQN-1161196Distributional Reinforcement Learning with Quantile Regression
MuZero (Res2 Adam)158541.58Online and Offline Reinforcement Learning by Planning with a Learned Model
Duel noop143570.0Dueling Network Architectures for Deep Reinforcement Learning
Prior noop141161.0Prioritized Experience Replay
A3C LSTM hs138518.0Asynchronous Methods for Deep Reinforcement Learning
0 of 49 row(s) selected.