Atari Games On Atari 2600 Battle Zone

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	934134.88	Agent57: Outperforming the Atari Human Benchmark
MuZero	848623.00	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-H3	824360	Generalized Data Distribution Iteration	-
R2D2	751880.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
GDI-I3	478830	Generalized Data Distribution Iteration	-
MuZero (Res2 Adam)	178716.9	Online and Offline Reinforcement Learning by Planning with a Learned Model
Ape-X	98895	Distributed Prioritized Experience Replay
FQF	87928.6	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
DNA	71003	DNA: Proximal Policy Optimization with a Dual Network Architecture
UCT	70333.3	The Arcade Learning Environment: An Evaluation Platform for General Agents
Reactor 500M	64070.0	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning	-
NoisyNet-Dueling	52262	Noisy Networks for Exploration
IQN	42244	Implicit Quantile Networks for Distributional Reinforcement Learning
DreamerV2	40325	Mastering Atari with Discrete World Models
QR-DQN-1	39268	Distributional Reinforcement Learning with Quantile Regression
ASL DDQN	38986	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Bootstrapped DQN	38666.7	Deep Exploration via Bootstrapped DQN
Duel noop	37150.0	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel noop	35520.0	Dueling Network Architectures for Deep Reinforcement Learning
Persistent AL	34583.07	Increasing the Action Gap: New Operators for Reinforcement Learning

0 of 47 row(s) selected.