Atari Games On Atari 2600 Crazy Climber

Metrics

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
C51 noop	179877.0	A Distributional Perspective on Reinforcement Learning	-
A3C FF (1 day) hs	101624.0	Asynchronous Methods for Deep Reinforcement Learning	-
Prior noop	141161.0	Prioritized Experience Replay	-
GDI-I3	201000	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
GDI-I3	201000	Generalized Data Distribution Iteration	-
IMPALA (deep)	136950.00	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	-
Reactor 500M	236422.0	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning	-
DDQN+Pop-Art noop	119679.0	Learning values across many orders of magnitude	-
R2D2	366690.7	Recurrent Experience Replay in Distributed Reinforcement Learning	-
DreamerV2	161839	Mastering Atari with Discrete World Models	-
Duel noop	143570.0	Dueling Network Architectures for Deep Reinforcement Learning	-
DDQN (tuned) noop	117282.0	Dueling Network Architectures for Deep Reinforcement Learning	-
IQN	179082	Implicit Quantile Networks for Distributional Reinforcement Learning	-
FQF	223470.6	Fully Parameterized Quantile Function for Distributional Reinforcement Learning	-
A3C FF hs	112646.0	Asynchronous Methods for Deep Reinforcement Learning	-
ASL DDQN	166019	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
Ape-X	320426	Distributed Prioritized Experience Replay	-
CGP	12900	Evolving simple programs for playing Atari games	-
Bootstrapped DQN	137925.9	Deep Exploration via Bootstrapped DQN	-
Agent57	565909.85	Agent57: Outperforming the Atari Human Benchmark	-

0 of 49 row(s) selected.