Atari Games On Atari 2600 Qbert

Score

Results

Performance results of various models on this benchmark

		Paper Title
Agent57	580328.14	Agent57: Outperforming the Atari Human Benchmark
QR-DQN-1	572510	Distributional Reinforcement Learning with Quantile Regression
R2D2	408850.0	Recurrent Experience Replay in Distributed Reinforcement Learning
IMPALA (deep)	351200.12	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Ape-X	302391.3	Distributed Prioritized Experience Replay
A2C + SIL	104975.6	Self-Imitation Learning
MuZero (Res2 Adam)	94906.25	Online and Offline Reinforcement Learning by Planning with a Learned Model
DreamerV2	94688	Mastering Atari with Discrete World Models
MuZero	72276.00	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
DNA	52398	DNA: Proximal Policy Optimization with a Dual Network Architecture
GDI-H3(200M frames)	28657	Generalized Data Distribution Iteration
GDI-H3	28657	Generalized Data Distribution Iteration
GDI-I3	27800	Generalized Data Distribution Iteration
GDI-I3	27800	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
NoisyNet-Dueling	27121	Noisy Networks for Exploration
IQN	25750	Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN	24548.8	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
C51 noop	23784	A Distributional Perspective on Reinforcement Learning
A3C LSTM hs	21307.5	Asynchronous Methods for Deep Reinforcement Learning
Duel noop	19220.3	Dueling Network Architectures for Deep Reinforcement Learning

0 of 57 row(s) selected.