Atari Games On Atari 2600 Kangaroo

Score

Results

Performance results of various models on this benchmark

		Paper Title
Agent57	24034.16	Agent57: Outperforming the Atari Human Benchmark
MuZero	16763.60	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Prior noop	16200.0	Prioritized Experience Replay
IQN	15487	Implicit Quantile Networks for Distributional Reinforcement Learning
QR-DQN-1	15356	Distributional Reinforcement Learning with Quantile Regression
NoisyNet-Dueling	15227	Noisy Networks for Exploration
Bootstrapped DQN	14862.5	Deep Exploration via Bootstrapped DQN
Duel noop	14854.0	Dueling Network Architectures for Deep Reinforcement Learning
GDI-H3	14636	Generalized Data Distribution Iteration
GDI-I3	14500	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
GDI-I3	14500	Generalized Data Distribution Iteration
DNA	14373	DNA: Proximal Policy Optimization with a Dual Network Architecture
R2D2	14130.7	Recurrent Experience Replay in Distributed Reinforcement Learning
DreamerV2	14064	Mastering Atari with Discrete World Models
MuZero (Res2 Adam)	13838	Online and Offline Reinforcement Learning by Planning with a Learned Model
DDQN+Pop-Art noop	13150.0	Learning values across many orders of magnitude
ASL DDQN	13027	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
DDQN (tuned) noop	12992.0	Dueling Network Architectures for Deep Reinforcement Learning
C51 noop	12853.0	A Distributional Perspective on Reinforcement Learning
Prior hs	12185.0	Prioritized Experience Replay

0 of 47 row(s) selected.