HyperAIHyperAI

Command Palette

Search for a command to run...

Plateforme

Atari Games On Atari 2600 Berzerk

Métriques

Score

Résultats

Résultats de performance de divers modèles sur ce benchmark

Paper Title
Go-Explore197376First return, then explore
MuZero85932.60Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent5761507.83Agent57: Outperforming the Atari Human Benchmark
Ape-X57196.7Distributed Prioritized Experience Replay
R2D253318.7Recurrent Experience Replay in Distributed Reinforcement Learning
DNA19789DNA: Proximal Policy Optimization with a Dual Network Architecture
GDI-H314649Generalized Data Distribution Iteration
FQF12422.2Fully Parameterized Quantile Function for Distributional Reinforcement Learning
GDI-I37607GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
GDI-I37607Generalized Data Distribution Iteration
Prior+Duel noop3409.0Dueling Network Architectures for Deep Reinforcement Learning
QR-DQN-13117Distributional Reinforcement Learning with Quantile Regression
MuZero (Res2 Adam)2705.82Online and Offline Reinforcement Learning by Planning with a Learned Model
ASL DDQN2597.2Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Reactor 500M2303.1The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
Prior+Duel hs2178.6Deep Reinforcement Learning with Double Q-learning
NoisyNet-Dueling1896Noisy Networks for Exploration
IMPALA (deep)1852.70IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
C51 noop1645.0A Distributional Perspective on Reinforcement Learning
Duel noop1472.6Dueling Network Architectures for Deep Reinforcement Learning
0 of 39 row(s) selected.
Atari Games On Atari 2600 Berzerk | SOTA | HyperAI