Atari Games On Atari 2600 Zaxxon

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	725853.90	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57	249808.9	Agent57: Outperforming the Atari Human Benchmark
R2D2	224910.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
GDI-H3	216020	Generalized Data Distribution Iteration	-
MuZero (Res2 Adam)	154131.86	Online and Offline Reinforcement Learning by Planning with a Learned Model
GDI-I3	109140	Generalized Data Distribution Iteration	-
DreamerV2	50699	Mastering Atari with Discrete World Models
Ape-X	42285.5	Distributed Prioritized Experience Replay
IMPALA (deep)	32935.50	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
A3C FF hs	24622.0	Asynchronous Methods for Deep Reinforcement Learning
A3C LSTM hs	23519.0	Asynchronous Methods for Deep Reinforcement Learning
UCT	22610	The Arcade Learning Environment: An Evaluation Platform for General Agents
DNA	22588	DNA: Proximal Policy Optimization with a Dual Network Architecture
IQN	21772	Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN	16420	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
RIMs-PPO	15000	Recurrent Independent Mechanisms
NoisyNet-Dueling	14874	Noisy Networks for Exploration
DDQN+Pop-Art noop	14402.0	Learning values across many orders of magnitude	-
Prior+Duel noop	13886.0	Dueling Network Architectures for Deep Reinforcement Learning
QR-DQN-1	13112	Distributional Reinforcement Learning with Quantile Regression

0 of 41 row(s) selected.