Atari Games On Atari 2600 Name This Game

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
MuZero	157177.85	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero (Res2 Adam)	101197.71	Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2	58182.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Agent57	54386.77	Agent57: Outperforming the Atari Human Benchmark
GDI-H3	36296	Generalized Data Distribution Iteration	-
GDI-I3	34434	Generalized Data Distribution Iteration	-
GDI-I3	34434	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Ape-X	25783.3	Distributed Prioritized Experience Replay
IQN	22682	Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-1	21890	Distributional Reinforcement Learning with Quantile Regression
IMPALA (deep)	21537.20	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DNA	20226	DNA: Proximal Policy Optimization with a Dual Network Architecture
ASL DDQN	16535.4	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
DDQN+Pop-Art noop	15851.2	Learning values across many orders of magnitude	-
Prior+Duel noop	15572.5	Dueling Network Architectures for Deep Reinforcement Learning
UCT	15410	The Arcade Learning Environment: An Evaluation Platform for General Agents
A2C + SIL	14958.2	Self-Imitation Learning
DreamerV2	14649	Mastering Atari with Discrete World Models
Prior+Duel hs	13637.9	Deep Reinforcement Learning with Double Q-learning
C51 noop	12542.0	A Distributional Perspective on Reinforcement Learning

0 of 43 row(s) selected.