HyperAI
HyperAI超神经
首页
资讯
最新论文
教程
数据集
百科
SOTA
LLM 模型天梯
GPU 天梯
顶会
开源项目
全站搜索
关于
中文
HyperAI
HyperAI超神经
Toggle sidebar
全站搜索…
⌘
K
首页
SOTA
Atari 游戏
Atari Games On Atari 2600 Fishing Derby
Atari Games On Atari 2600 Fishing Derby
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
Columns
模型名称
Score
Paper Title
Repository
IMPALA (deep)
44.85
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
-
FQF
52.7
Fully Parameterized Quantile Function for Distributional Reinforcement Learning
-
Duel hs
-4.1
Dueling Network Architectures for Deep Reinforcement Learning
-
DDQN+Pop-Art noop
45.1
Learning values across many orders of magnitude
-
DQN noop
-4.9
Deep Reinforcement Learning with Double Q-learning
-
POP3D
28.99
Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
-
CGP
-51
Evolving simple programs for playing Atari games
-
Duel noop
46.4
Dueling Network Architectures for Deep Reinforcement Learning
-
GDI-I3
59
Generalized Data Distribution Iteration
-
NoisyNet-Dueling
57
Noisy Networks for Exploration
-
QR-DQN-1
39
Distributional Reinforcement Learning with Quantile Regression
-
Ape-X
44.4
Distributed Prioritized Experience Replay
-
Advantage Learning
21.32
Increasing the Action Gap: New Operators for Reinforcement Learning
-
Best Learner
-89.5
The Arcade Learning Environment: An Evaluation Platform for General Agents
-
Prior hs
9.8
Prioritized Experience Replay
-
DreamerV2
65
Mastering Atari with Discrete World Models
-
A2C + SIL
55.8
Self-Imitation Learning
-
IDVQ + DRSC + XNES
-10
Playing Atari with Six Neurons
-
R2D2
85.8
Recurrent Experience Replay in Distributed Reinforcement Learning
-
GDI-I3
59
GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
-
0 of 44 row(s) selected.
Previous
Next