HyperAIHyperAI

Command Palette

Search for a command to run...

Plattform

Atari Games On Atari 2600 Asteroids

Metriken

Score

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Paper Title
GDI-H3760005Generalized Data Distribution Iteration
GDI-I3751970Generalized Data Distribution Iteration
MuZero678558.64Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
MuZero (Res2 Adam)476412Online and Offline Reinforcement Learning by Planning with a Learned Model
R2D2357867.7Recurrent Experience Replay in Distributed Reinforcement Learning
DNA165973DNA: Proximal Policy Optimization with a Dual Network Architecture
Ape-X155495.1Distributed Prioritized Experience Replay
Agent57150854.61Agent57: Outperforming the Atari Human Benchmark
IMPALA (deep)108590.05IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
NoisyNet-Dueling86700Noisy Networks for Exploration
DreamerV241526Mastering Atari with Discrete World Models
CGP9412Evolving simple programs for playing Atari games
A3C LSTM hs5093.1Asynchronous Methods for Deep Reinforcement Learning
UCT4660.6The Arcade Learning Environment: An Evaluation Platform for General Agents
FQF4553.0Fully Parameterized Quantile Function for Distributional Reinforcement Learning
A3C FF hs4474.5Asynchronous Methods for Deep Reinforcement Learning
QR-DQN-14226Distributional Reinforcement Learning with Quantile Regression
Reactor 500M3726.1The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning
A3C FF (1 day) hs3009.4Asynchronous Methods for Deep Reinforcement Learning
IQN2898Implicit Quantile Networks for Distributional Reinforcement Learning
0 of 43 row(s) selected.