Atari Games On Atari 2600 James Bond

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	620780	Generalized Data Distribution Iteration	-
GDI-I3	594500	Generalized Data Distribution Iteration	-
GDI-I3	594500	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Agent57	135784.96	Agent57: Outperforming the Atari Human Benchmark
FQF	87291.7	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
MuZero	41063.25	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
DreamerV2	40445	Mastering Atari with Discrete World Models
IQN	35108	Implicit Quantile Networks for Distributional Reinforcement Learning
MuZero (Res2 Adam)	28626.23	Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2	25354.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
Ape-X	21322.5	Distributed Prioritized Experience Replay
DNA	14102	DNA: Proximal Policy Optimization with a Dual Network Architecture
CGP	6130	Evolving simple programs for playing Atari games
Prior noop	5148.0	Prioritized Experience Replay
QR-DQN-1	4703	Distributional Reinforcement Learning with Quantile Regression
Prior hs	3961.0	Prioritized Experience Replay
ASL DDQN	2237	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
C51 noop	1909.0	A Distributional Perspective on Reinforcement Learning
Bootstrapped DQN	1663.5	Deep Exploration via Bootstrapped DQN
DDQN (tuned) noop	1358.0	Dueling Network Architectures for Deep Reinforcement Learning

0 of 45 row(s) selected.