Atari Games On Atari 2600 Up And Down

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 Title	Repository
GDI-I3	986440	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-I3	986440	Generalized Data Distribution Iteration	-
GDI-H3	966590	Generalized Data Distribution Iteration	-
MuZero	715545.61	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
DreamerV2	653662	Mastering Atari with Discrete World Models
MuZero (Res2 Adam)	634898.18	Online and Offline Reinforcement Learning by Planning with a Learned Model
Agent57	623805.73	Agent57: Outperforming the Atari Human Benchmark
R2D2	589226.9	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Ape-X	401884.3	Distributed Prioritized Experience Replay
RIMs-PPO	390000	Recurrent Independent Mechanisms
IMPALA (deep)	332546.75	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DNA	291934	DNA: Proximal Policy Optimization with a Dual Network Architecture
POP3D	242701.51	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
A3C LSTM hs	105728.7	Asynchronous Methods for Deep Reinforcement Learning
IQN	88148	Implicit Quantile Networks for Distributional Reinforcement Learning
A3C FF hs	74705.7	Asynchronous Methods for Deep Reinforcement Learning
UCT	74473.6	The Arcade Learning Environment: An Evaluation Platform for General Agents
QR-DQN-1	71260	Distributional Reinforcement Learning with Quantile Regression
ES FF (1 hour) noop	67974.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning
NoisyNet-Dueling	61326	Noisy Networks for Exploration

0 of 44 row(s) selected.