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 Amidar

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
VPN641Value Prediction Network-
R2D229321.4Recurrent Experience Replay in Distributed Reinforcement Learning-
A3C FF (1 day) hs283.9Asynchronous Methods for Deep Reinforcement Learning-
GDI-I31442Generalized Data Distribution Iteration-
CURL232.3CURL: Contrastive Unsupervised Representations for Reinforcement Learning-
DreamerV22577Mastering Atari with Discrete World Models-
Nature DQN739.5Human level control through deep reinforcement learning
Ape-X8659.2Distributed Prioritized Experience Replay-
Prior+Duel hs238.4Dueling Network Architectures for Deep Reinforcement Learning-
Prior+Duel hs238.4Deep Reinforcement Learning with Double Q-learning-
POP3D729.15Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization-
DQN noop978.0Deep Reinforcement Learning with Double Q-learning-
Rainbow+SEER250.5Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings-
A2C + SIL1362Self-Imitation Learning-
Reactor 500M1015.8The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning-
C51 noop1735.0A Distributional Perspective on Reinforcement Learning-
ASL DDQN2232.3Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
Agent5729660.08Agent57: Outperforming the Atari Human Benchmark-
QR-DQN-11641Distributional Reinforcement Learning with Quantile Regression-
Persistent AL1451.65Increasing the Action Gap: New Operators for Reinforcement Learning-
0 of 48 row(s) selected.