HyperAIHyperAI超神経

Command Palette

Search for a command to run...

プラットフォーム

Atari Games On Atari 2600 Asterix

評価指標

Score

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

Paper Title
GDI-H3999999Generalized Data Distribution Iteration
R2D2999153.3Recurrent Experience Replay in Distributed Reinforcement Learning
MuZero998425.00Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57991384.42Agent57: Outperforming the Atari Human Benchmark
MuZero (Res2 Adam)862406.65Online and Offline Reinforcement Learning by Planning with a Learned Model
GDI-I3759910Generalized Data Distribution Iteration
FQF578388.5Fully Parameterized Quantile Function for Distributional Reinforcement Learning
ASL DDQN567640Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
C51 noop406211A Distributional Perspective on Reinforcement Learning
Prior+Duel noop375080.0Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel hs364200.0Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel hs364200.0Deep Reinforcement Learning with Double Q-learning
IQN342016Implicit Quantile Networks for Distributional Reinforcement Learning
DNA323965DNA: Proximal Policy Optimization with a Dual Network Architecture
Ape-X313305Distributed Prioritized Experience Replay
IMPALA (deep)300732.00IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
UCT290700The Arcade Learning Environment: An Evaluation Platform for General Agents
QR-DQN-1261025Distributional Reinforcement Learning with Quantile Regression
Reactor 500M205914.0The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
DreamerV272311Mastering Atari with Discrete World Models
0 of 49 row(s) selected.
Atari Games On Atari 2600 Asterix | SOTA | HyperAI超神経