Atari Games On Atari 2600 Enduro

评估指标

Score

评测结果

各个模型在此基准测试上的表现结果

模型名称	Score	Paper Title	Repository
DQN hs	626.7	Deep Reinforcement Learning with Double Q-learning	-
Advantage Learning	1252.7	Increasing the Action Gap: New Operators for Reinforcement Learning	-
IQN	2359	Implicit Quantile Networks for Distributional Reinforcement Learning	-
DQN Best	661	Playing Atari with Deep Reinforcement Learning	-
Prior noop	2093.0	Prioritized Experience Replay	-
DNA	2059	DNA: Proximal Policy Optimization with a Dual Network Architecture	-
ASL DDQN	2103.1	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
Nature DQN	301.8	Human level control through deep reinforcement learning
Persistent AL	1343.1	Increasing the Action Gap: New Operators for Reinforcement Learning	-
Prior+Duel noop	2306.4	Dueling Network Architectures for Deep Reinforcement Learning	-
A3C FF hs	-82.5	Asynchronous Methods for Deep Reinforcement Learning	-
A3C LSTM hs	-82.5	Asynchronous Methods for Deep Reinforcement Learning	-
CGP	56.8	Evolving simple programs for playing Atari games	-
UCT	286.3	The Arcade Learning Environment: An Evaluation Platform for General Agents	-
GDI-I3	14330	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning	-
Duel hs	2077.4	Dueling Network Architectures for Deep Reinforcement Learning	-
Rational DQN Average	1043	Adaptive Rational Activations to Boost Deep Reinforcement Learning	-
DQN noop	729.0	Deep Reinforcement Learning with Double Q-learning	-
VPN	382	Value Prediction Network	-
Duel noop	2258.2	Dueling Network Architectures for Deep Reinforcement Learning	-

0 of 48 row(s) selected.