Atari Games On Atari 2600 Crazy Climber

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
Agent57	565909.85	Agent57: Outperforming the Atari Human Benchmark
MuZero	458315.40	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D2	366690.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Ape-X	320426	Distributed Prioritized Experience Replay
GDI-H3	241170	Generalized Data Distribution Iteration	-
Reactor 500M	236422.0	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning	-
FQF	223470.6	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
GDI-I3	201000	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-I3	201000	Generalized Data Distribution Iteration	-
C51 noop	179877.0	A Distributional Perspective on Reinforcement Learning
IQN	179082	Implicit Quantile Networks for Distributional Reinforcement Learning
NoisyNet-Dueling	171171	Noisy Networks for Exploration
ASL DDQN	166019	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior+Duel noop	162224.0	Dueling Network Architectures for Deep Reinforcement Learning
DreamerV2	161839	Mastering Atari with Discrete World Models
QR-DQN-1	161196	Distributional Reinforcement Learning with Quantile Regression
MuZero (Res2 Adam)	158541.58	Online and Offline Reinforcement Learning by Planning with a Learned Model
Duel noop	143570.0	Dueling Network Architectures for Deep Reinforcement Learning
Prior noop	141161.0	Prioritized Experience Replay
A3C LSTM hs	138518.0	Asynchronous Methods for Deep Reinforcement Learning

0 of 49 row(s) selected.