HyperAI초신경
홈뉴스최신 연구 논문튜토리얼데이터셋백과사전SOTALLM 모델GPU 랭킹컨퍼런스
전체 검색
소개
HyperAI초신경

Atari Games On Atari 2600 Road Runner

평가 지표

Score

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름
Score
Paper TitleRepository
CURL6786.7CURL: Contrastive Unsupervised Representations for Reinforcement Learning
MuZero613411.80Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D2599246.7Recurrent Experience Replay in Distributed Reinforcement Learning-
QR-DQN-164262Distributional Reinforcement Learning with Quantile Regression
C51 noop55839.0A Distributional Perspective on Reinforcement Learning
IMPALA (deep)57121.00IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Duel hs58549.0Dueling Network Architectures for Deep Reinforcement Learning
A2C + SIL57071.7Self-Imitation Learning
Agent57243025.8Agent57: Outperforming the Atari Human Benchmark
IQN57900Implicit Quantile Networks for Distributional Reinforcement Learning
DQN hs35215.0Deep Reinforcement Learning with Double Q-learning
GDI-H3999999Generalized Data Distribution Iteration-
Best Learner67.7The Arcade Learning Environment: An Evaluation Platform for General Agents
Prior+Duel hs54630.0Deep Reinforcement Learning with Double Q-learning
DDQN (tuned) hs43156.0Deep Reinforcement Learning with Double Q-learning
GDI-I3878600Generalized Data Distribution Iteration-
Duel noop69524.0Dueling Network Architectures for Deep Reinforcement Learning
DNA61713DNA: Proximal Policy Optimization with a Dual Network Architecture
SAC305.3Soft Actor-Critic for Discrete Action Settings
ASL DDQN56520Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity-
0 of 44 row(s) selected.