Atari Games On Atari 2600 Amidar

評価指標

Score

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	Score	Paper Title	Repository
VPN	641	Value Prediction Network
R2D2	29321.4	Recurrent Experience Replay in Distributed Reinforcement Learning	-
A3C FF (1 day) hs	283.9	Asynchronous Methods for Deep Reinforcement Learning
GDI-I3	1442	Generalized Data Distribution Iteration	-
CURL	232.3	CURL: Contrastive Unsupervised Representations for Reinforcement Learning
DreamerV2	2577	Mastering Atari with Discrete World Models
Nature DQN	739.5	Human level control through deep reinforcement learning
Ape-X	8659.2	Distributed Prioritized Experience Replay
Prior+Duel hs	238.4	Dueling Network Architectures for Deep Reinforcement Learning
Prior+Duel hs	238.4	Deep Reinforcement Learning with Double Q-learning
POP3D	729.15	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization
DQN noop	978.0	Deep Reinforcement Learning with Double Q-learning
Rainbow+SEER	250.5	Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings
A2C + SIL	1362	Self-Imitation Learning
Reactor 500M	1015.8	The Reactor: A fast and sample-efficient Actor-Critic agent for Reinforcement Learning	-
C51 noop	1735.0	A Distributional Perspective on Reinforcement Learning
ASL DDQN	2232.3	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
Agent57	29660.08	Agent57: Outperforming the Atari Human Benchmark
QR-DQN-1	1641	Distributional Reinforcement Learning with Quantile Regression
Persistent AL	1451.65	Increasing the Action Gap: New Operators for Reinforcement Learning

0 of 48 row(s) selected.