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

中文

HyperAI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

模型名称	Score	Paper Title	Repository
QR-DQN-1	26447	Distributional Reinforcement Learning with Quantile Regression
ASL DDQN	29231.9	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
R2D2	995048.4	Recurrent Experience Replay in Distributed Reinforcement Learning	-
MuZero	553311.46	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Advantage Learning	24240.03	Increasing the Action Gap: New Operators for Reinforcement Learning
CGP	28838.2	Evolving simple programs for playing Atari games
Ape-X	148594.8	Distributed Prioritized Experience Replay
DNA	564513	DNA: Proximal Policy Optimization with a Dual Network Architecture
DreamerV2	156748	Mastering Atari with Discrete World Models
IMPALA (deep)	84231.14	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
RUDDER	60577	RUDDER: Return Decomposition for Delayed Rewards
NoisyNet-Dueling	86101	Noisy Networks for Exploration
GDI-H3	968090	Generalized Data Distribution Iteration	-
GDI-I3	972000	Generalized Data Distribution Iteration	-
MuZero (Res2 Adam)	219838.09	Online and Offline Reinforcement Learning by Planning with a Learned Model
IQN	28379	Implicit Quantile Networks for Distributional Reinforcement Learning
Agent57	998532.37	Agent57: Outperforming the Atari Human Benchmark

0 of 17 row(s) selected.