Atari Games On Atari 2600 Road Runner

Métriques

Score

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Score	Paper Title	Repository
CURL	6786.7	CURL: Contrastive Unsupervised Representations for Reinforcement Learning
MuZero	613411.80	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
R2D2	599246.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
QR-DQN-1	64262	Distributional Reinforcement Learning with Quantile Regression
C51 noop	55839.0	A Distributional Perspective on Reinforcement Learning
IMPALA (deep)	57121.00	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Duel hs	58549.0	Dueling Network Architectures for Deep Reinforcement Learning
A2C + SIL	57071.7	Self-Imitation Learning
Agent57	243025.8	Agent57: Outperforming the Atari Human Benchmark
IQN	57900	Implicit Quantile Networks for Distributional Reinforcement Learning
DQN hs	35215.0	Deep Reinforcement Learning with Double Q-learning
GDI-H3	999999	Generalized Data Distribution Iteration	-
Best Learner	67.7	The Arcade Learning Environment: An Evaluation Platform for General Agents
Prior+Duel hs	54630.0	Deep Reinforcement Learning with Double Q-learning
DDQN (tuned) hs	43156.0	Deep Reinforcement Learning with Double Q-learning
GDI-I3	878600	Generalized Data Distribution Iteration	-
Duel noop	69524.0	Dueling Network Architectures for Deep Reinforcement Learning
DNA	61713	DNA: Proximal Policy Optimization with a Dual Network Architecture
SAC	305.3	Soft Actor-Critic for Discrete Action Settings
ASL DDQN	56520	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-

0 of 44 row(s) selected.