Atari Games On Atari 2600 Defender

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
CGP	993010	Evolving simple programs for playing Atari games
GDI-H3	970540	Generalized Data Distribution Iteration	-
GDI-I3	893110	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-I3	893110	Generalized Data Distribution Iteration	-
MuZero	839642.95	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57	677642.78	Agent57: Outperforming the Atari Human Benchmark
R2D2	665792.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
MuZero (Res2 Adam)	557200.75	Online and Offline Reinforcement Learning by Planning with a Learned Model
Ape-X	411943.5	Distributed Prioritized Experience Replay
Reactor 500M	223025.0	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning	-
IMPALA (deep)	185203.00	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DNA	152768	DNA: Proximal Policy Optimization with a Dual Network Architecture
IQN	53537	Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-1	47887	Distributional Reinforcement Learning with Quantile Regression
NoisyNet-Dueling	42253	Noisy Networks for Exploration
Duel noop	42214.0	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop	41324.5	Dueling Network Architectures for Deep Reinforcement Learning
ASL DDQN	37026.5	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior+Duel hs	34415.0	Dueling Network Architectures for Deep Reinforcement Learning
Persistent AL	32038.93	Increasing the Action Gap: New Operators for Reinforcement Learning

0 of 21 row(s) selected.