HyperAI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
HyperAI超神经

Atari Games On Atari 2600 Atlantis

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
IQN978200Implicit Quantile Networks for Distributional Reinforcement Learning
C51 noop841075.0A Distributional Perspective on Reinforcement Learning
DDQN (tuned) noop106056.0Dueling Network Architectures for Deep Reinforcement Learning
Duel noop382572.0Dueling Network Architectures for Deep Reinforcement Learning
NoisyNet-Dueling972175Noisy Networks for Exploration
Ape-X944497.5Distributed Prioritized Experience Replay
Prior noop357324.0Prioritized Experience Replay
GDI-I33803000Generalized Data Distribution Iteration-
Persistent AL1465250Increasing the Action Gap: New Operators for Reinforcement Learning
UCT193858The Arcade Learning Environment: An Evaluation Platform for General Agents
Bootstrapped DQN994500Deep Exploration via Bootstrapped DQN
ASL DDQN947275Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
A3C LSTM hs875822.0Asynchronous Methods for Deep Reinforcement Learning
QR-DQN-1971850Distributional Reinforcement Learning with Quantile Regression
ES FF (1 hour) noop1267410.0Evolution Strategies as a Scalable Alternative to Reinforcement Learning
Nature DQN85641.0Human level control through deep reinforcement learning
Advantage Learning553591.67Increasing the Action Gap: New Operators for Reinforcement Learning
DDQN (tuned) hs319688.0Deep Reinforcement Learning with Double Q-learning
Agent571528841.76Agent57: Outperforming the Atari Human Benchmark
POP3D2193605.67Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
0 of 42 row(s) selected.