Atari Games On Atari 2600 Bank Heist

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 (Res2 Adam)	27219.8	Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2	24235.9	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Agent57	23071.5	Agent57: Outperforming the Atari Human Benchmark
Ape-X	1716.4	Distributed Prioritized Experience Replay
Duel noop	1611.9	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop	1503.1	Dueling Network Architectures for Deep Reinforcement Learning
IQN	1416	Implicit Quantile Networks for Distributional Reinforcement Learning
GDI-I3	1401	Generalized Data Distribution Iteration	-
GDI-H3	1380	Generalized Data Distribution Iteration	-
ASL DDQN	1340.9	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
NoisyNet-Dueling	1318	Noisy Networks for Exploration
DNA	1286	DNA: Proximal Policy Optimization with a Dual Network Architecture
MuZero	1278.98	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Reactor 500M	1259.7	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning	-
QR-DQN-1	1249	Distributional Reinforcement Learning with Quantile Regression
IMPALA (deep)	1223.15	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
POP3D	1212.23	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
Bootstrapped DQN	1208	Deep Exploration via Bootstrapped DQN
A2C + SIL	1137.8	Self-Imitation Learning
Duel hs	1129.3	Dueling Network Architectures for Deep Reinforcement Learning

0 of 45 row(s) selected.