HyperAI초신경

홈 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Atari Games On Atari 2600 Surround

평가 지표

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Score	Paper Title	Repository
MuZero (Res2 Adam)	9.9	Online and Offline Reinforcement Learning by Planning with a Learned Model
Agent57	9.5	Agent57: Outperforming the Atari Human Benchmark
DNA	5.3	DNA: Proximal Policy Optimization with a Dual Network Architecture
Persistent AL	0.72	Increasing the Action Gap: New Operators for Reinforcement Learning
GDI-H3	2.606	Generalized Data Distribution Iteration	-
IMPALA (deep)	7.56	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
NoisyNet-Dueling	10	Noisy Networks for Exploration
GDI-I3	-7.8	Generalized Data Distribution Iteration	-
Ape-X	7.1	Distributed Prioritized Experience Replay
QR-DQN-1	8.2	Distributional Reinforcement Learning with Quantile Regression
ASL DDQN	2.5	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
R2D2	9.9	Recurrent Experience Replay in Distributed Reinforcement Learning	-
IQN	9.4	Implicit Quantile Networks for Distributional Reinforcement Learning
MuZero	9.99	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-I3	-7.8	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-

0 of 15 row(s) selected.