Atari Games On Atari 2600 Phoenix

Metrics

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
IMPALA (deep)	210996.45	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	-
Advantage Learning	22038.27	Increasing the Action Gap: New Operators for Reinforcement Learning	-
MuZero	955137.84	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	-
FQF	174077.5	Fully Parameterized Quantile Function for Distributional Reinforcement Learning	-
QR-DQN-1	16585	Distributional Reinforcement Learning with Quantile Regression	-
GDI-I3	894460	Generalized Data Distribution Iteration	-
ASL DDQN	71752.6	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
R2D2	864020.0	Recurrent Experience Replay in Distributed Reinforcement Learning	-
DNA	391085	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
GDI-I3	894460	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Prior+Duel hs	63597.0	Dueling Network Architectures for Deep Reinforcement Learning	-
IQN	56599	Implicit Quantile Networks for Distributional Reinforcement Learning	-
Agent57	908264.15	Agent57: Outperforming the Atari Human Benchmark	-
Ape-X	224491.1	Distributed Prioritized Experience Replay	-
Persistent AL	14495.56	Increasing the Action Gap: New Operators for Reinforcement Learning	-
GDI-H3	959580	Generalized Data Distribution Iteration	-
NoisyNet-Dueling	10379	Noisy Networks for Exploration	-
MuZero (Res2 Adam)	815728.7	Online and Offline Reinforcement Learning by Planning with a Learned Model	-
DreamerV2	49375	Mastering Atari with Discrete World Models	-
CGP	7520	Evolving simple programs for playing Atari games	-

0 of 21 row(s) selected.