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 Crazy Climber

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
C51 noop179877.0A Distributional Perspective on Reinforcement Learning
A3C FF (1 day) hs101624.0Asynchronous Methods for Deep Reinforcement Learning
Prior noop141161.0Prioritized Experience Replay
GDI-I3201000GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning-
GDI-I3201000Generalized Data Distribution Iteration-
IMPALA (deep)136950.00IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Reactor 500M236422.0The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning-
DDQN+Pop-Art noop119679.0Learning values across many orders of magnitude-
R2D2366690.7Recurrent Experience Replay in Distributed Reinforcement Learning-
DreamerV2161839Mastering Atari with Discrete World Models
Duel noop143570.0Dueling Network Architectures for Deep Reinforcement Learning
DDQN (tuned) noop117282.0Dueling Network Architectures for Deep Reinforcement Learning
IQN179082Implicit Quantile Networks for Distributional Reinforcement Learning
FQF223470.6Fully Parameterized Quantile Function for Distributional Reinforcement Learning
A3C FF hs112646.0Asynchronous Methods for Deep Reinforcement Learning
ASL DDQN166019Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
Ape-X320426Distributed Prioritized Experience Replay
CGP12900Evolving simple programs for playing Atari games
Bootstrapped DQN137925.9Deep Exploration via Bootstrapped DQN
Agent57565909.85Agent57: Outperforming the Atari Human Benchmark
0 of 49 row(s) selected.