Atari Games On Atari 2600 Time Pilot

Metrics

Score

Results

Performance results of various models on this benchmark

		Paper Title	Repository
MuZero	476763.90	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
GDI-H3	450810	Generalized Data Distribution Iteration	-
R2D2	445377.3	Recurrent Experience Replay in Distributed Reinforcement Learning	-
MuZero (Res2 Adam)	424011.16	Online and Offline Reinforcement Learning by Planning with a Learned Model
Agent57	405425.31	Agent57: Outperforming the Atari Human Benchmark
GDI-I3	216770	Generalized Data Distribution Iteration	-
GDI-I3	216770	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Ape-X	87085	Distributed Prioritized Experience Replay
UCT	63854.5	The Arcade Learning Environment: An Evaluation Platform for General Agents
IMPALA (deep)	48481.50	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DreamerV2	37945	Mastering Atari with Discrete World Models
A3C LSTM hs	27202.0	Asynchronous Methods for Deep Reinforcement Learning
Rational DQN Average	17632	Adaptive Rational Activations to Boost Deep Reinforcement Learning
NoisyNet-Dueling	17301	Noisy Networks for Exploration
Recurrent Rational DQN Average	13261	Adaptive Rational Activations to Boost Deep Reinforcement Learning
DNA	12774	DNA: Proximal Policy Optimization with a Dual Network Architecture
A3C FF hs	12679.0	Asynchronous Methods for Deep Reinforcement Learning
IQN	12236	Implicit Quantile Networks for Distributional Reinforcement Learning
ASL DDQN	12071	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
CGP	12040	Evolving simple programs for playing Atari games

0 of 44 row(s) selected.

Command Palette

Atari Games On Atari 2600 Time Pilot

Metrics

Results