Atari Games On Atari 2600 Krull

Score

Results

Performance results of various models on this benchmark

		Paper Title
GDI-H3	594540	Generalized Data Distribution Iteration
MuZero	269358.27	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
Agent57	251997.31	Agent57: Outperforming the Atari Human Benchmark
R2D2	218448.1	Recurrent Experience Replay in Distributed Reinforcement Learning
GDI-I3	97575	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning
GDI-I3	97575	Generalized Data Distribution Iteration
MuZero (Res2 Adam)	72570.5	Online and Offline Reinforcement Learning by Planning with a Learned Model
DreamerV2	50061	Mastering Atari with Discrete World Models
VPN	15930	Value Prediction Network
Ape-X	11741.4	Distributed Prioritized Experience Replay
Duel noop	11451.9	Dueling Network Architectures for Deep Reinforcement Learning
QR-DQN-1	11447	Distributional Reinforcement Learning with Quantile Regression
DNA	10956	DNA: Proximal Policy Optimization with a Dual Network Architecture
NoisyNet-Dueling	10754	Noisy Networks for Exploration
IQN	10707	Implicit Quantile Networks for Distributional Reinforcement Learning
A2C + SIL	10614.6	Self-Imitation Learning
ASL DDQN	10422.5	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity
Prior+Duel noop	10374.4	Dueling Network Architectures for Deep Reinforcement Learning
DDQN+Pop-Art noop	9745.1	Learning values across many orders of magnitude
C51 noop	9735.0	A Distributional Perspective on Reinforcement Learning

0 of 45 row(s) selected.