Atari Games On Atari 2600 Atlantis

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-H3	3837300	Generalized Data Distribution Iteration	-
GDI-I3	3803000	Generalized Data Distribution Iteration	-
A2C + SIL	3084781.7	Self-Imitation Learning
POP3D	2193605.67	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
MuZero	1674767.20	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D2	1620764.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Agent57	1528841.76	Agent57: Outperforming the Atari Human Benchmark
Persistent AL	1465250	Increasing the Action Gap: New Operators for Reinforcement Learning
ES FF (1 hour) noop	1267410.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning
MuZero (Res2 Adam)	1137475.12	Online and Offline Reinforcement Learning by Planning with a Learned Model
Bootstrapped DQN	994500	Deep Exploration via Bootstrapped DQN
DreamerV2	978778	Mastering Atari with Discrete World Models
IQN	978200	Implicit Quantile Networks for Distributional Reinforcement Learning
NoisyNet-Dueling	972175	Noisy Networks for Exploration
QR-DQN-1	971850	Distributional Reinforcement Learning with Quantile Regression
ASL DDQN	947275	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Ape-X	944497.5	Distributed Prioritized Experience Replay
DNA	932559	DNA: Proximal Policy Optimization with a Dual Network Architecture
A3C FF hs	911091.0	Asynchronous Methods for Deep Reinforcement Learning
A3C LSTM hs	875822.0	Asynchronous Methods for Deep Reinforcement Learning

0 of 42 row(s) selected.