HyperAIHyperAI超神经
首页资讯最新论文教程数据集百科SOTALLM 模型天梯GPU 天梯顶会
全站搜索
关于
HyperAIHyperAI超神经

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 TitleRepository
IQN734Implicit Quantile Networks for Distributional Reinforcement Learning-
A3C FF (1 day) hs551.6Asynchronous Methods for Deep Reinforcement Learning-
UCT364.4The Arcade Learning Environment: An Evaluation Platform for General Agents-
SPOS Search space 1144.4Optimizing the Neural Architecture of Reinforcement Learning Agents-
FQF854.2Fully Parameterized Quantile Function for Distributional Reinforcement Learning-
Bootstrapped DQN855Deep Exploration via Bootstrapped DQN-
CGP13.2Evolving simple programs for playing Atari games-
MuZero (Res2 Adam)758.04Online and Offline Reinforcement Learning by Planning with a Learned Model-
Agent57790.4Agent57: Outperforming the Atari Human Benchmark-
ENAS Search space 1161.1Optimizing the Neural Architecture of Reinforcement Learning Agents-
Best Learner5.2The Arcade Learning Environment: An Evaluation Platform for General Agents-
ASL DDQN621.7Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
POP3D458.41Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization-
CURL18.2CURL: Contrastive Unsupervised Representations for Reinforcement Learning-
Prior+Duel hs354.6Deep Reinforcement Learning with Double Q-learning-
Prior noop373.9Prioritized Experience Replay-
Nature DQN401.2Human level control through deep reinforcement learning
Prior+Duel noop366.0Dueling Network Architectures for Deep Reinforcement Learning-
DT267.5Decision Transformer: Reinforcement Learning via Sequence Modeling-
DQN Best225Playing Atari with Deep Reinforcement Learning-
0 of 58 row(s) selected.