Atari Games On Atari 2600 Breakout

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

模型名称	Score	Paper Title	Repository
IQN	734	Implicit Quantile Networks for Distributional Reinforcement Learning
A3C FF (1 day) hs	551.6	Asynchronous Methods for Deep Reinforcement Learning
UCT	364.4	The Arcade Learning Environment: An Evaluation Platform for General Agents
SPOS Search space 1	144.4	Optimizing the Neural Architecture of Reinforcement Learning Agents
FQF	854.2	Fully Parameterized Quantile Function for Distributional Reinforcement Learning
Bootstrapped DQN	855	Deep Exploration via Bootstrapped DQN
CGP	13.2	Evolving simple programs for playing Atari games
MuZero (Res2 Adam)	758.04	Online and Offline Reinforcement Learning by Planning with a Learned Model
Agent57	790.4	Agent57: Outperforming the Atari Human Benchmark
ENAS Search space 1	161.1	Optimizing the Neural Architecture of Reinforcement Learning Agents
Best Learner	5.2	The Arcade Learning Environment: An Evaluation Platform for General Agents
ASL DDQN	621.7	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
POP3D	458.41	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
CURL	18.2	CURL: Contrastive Unsupervised Representations for Reinforcement Learning
Prior+Duel hs	354.6	Deep Reinforcement Learning with Double Q-learning
Prior noop	373.9	Prioritized Experience Replay
Nature DQN	401.2	Human level control through deep reinforcement learning
Prior+Duel noop	366.0	Dueling Network Architectures for Deep Reinforcement Learning
DT	267.5	Decision Transformer: Reinforcement Learning via Sequence Modeling
DQN Best	225	Playing Atari with Deep Reinforcement Learning

0 of 58 row(s) selected.