Atari Games On Atari 2600 Kung Fu Master

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	1666665	Generalized Data Distribution Iteration	-
GDI-H3 (200M)	1666000	GDI: Rethinking What Makes Reinforcement Learning Different from Supervised Learning	-
R2D2	233413.3	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Agent57	206845.82	Agent57: Outperforming the Atari Human Benchmark
MuZero	204824.00	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-I3	140440	Generalized Data Distribution Iteration	-
MuZero (Res2 Adam)	116726.96	Online and Offline Reinforcement Learning by Planning with a Learned Model
FQF	111138.5	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
DNA	110962	DNA: Proximal Policy Optimization with a Dual Network Architecture
Ape-X	97829.5	Distributed Prioritized Experience Replay
ASL DDQN	85182	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
QR-DQN-1	76642	Distributional Reinforcement Learning with Quantile Regression
IQN	73512	Implicit Quantile Networks for Distributional Reinforcement Learning
DreamerV2	62741	Mastering Atari with Discrete World Models
CGP	57400	Evolving simple programs for playing Atari games
UCT	48854.5	The Arcade Learning Environment: An Evaluation Platform for General Agents
Prior+Duel noop	48375.0	Dueling Network Architectures for Deep Reinforcement Learning
C51 noop	48192.0	A Distributional Perspective on Reinforcement Learning
IMPALA (deep)	43375.50	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
NoisyNet-Dueling	41672	Noisy Networks for Exploration

0 of 43 row(s) selected.