Atari Games On Atari 2600 Atlantis

Metrics

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
IQN	978200	Implicit Quantile Networks for Distributional Reinforcement Learning	-
C51 noop	841075.0	A Distributional Perspective on Reinforcement Learning	-
DDQN (tuned) noop	106056.0	Dueling Network Architectures for Deep Reinforcement Learning	-
Duel noop	382572.0	Dueling Network Architectures for Deep Reinforcement Learning	-
NoisyNet-Dueling	972175	Noisy Networks for Exploration	-
Ape-X	944497.5	Distributed Prioritized Experience Replay	-
Prior noop	357324.0	Prioritized Experience Replay	-
GDI-I3	3803000	Generalized Data Distribution Iteration	-
Persistent AL	1465250	Increasing the Action Gap: New Operators for Reinforcement Learning	-
UCT	193858	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
Bootstrapped DQN	994500	Deep Exploration via Bootstrapped DQN	-
ASL DDQN	947275	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
A3C LSTM hs	875822.0	Asynchronous Methods for Deep Reinforcement Learning	-
QR-DQN-1	971850	Distributional Reinforcement Learning with Quantile Regression	-
ES FF (1 hour) noop	1267410.0	Evolution Strategies as a Scalable Alternative to Reinforcement Learning	-
Nature DQN	85641.0	Human level control through deep reinforcement learning
Advantage Learning	553591.67	Increasing the Action Gap: New Operators for Reinforcement Learning	-
DDQN (tuned) hs	319688.0	Deep Reinforcement Learning with Double Q-learning	-
Agent57	1528841.76	Agent57: Outperforming the Atari Human Benchmark	-
POP3D	2193605.67	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization	-

0 of 42 row(s) selected.