Atari Games on Atari 2600 Space Invaders

110개 결과 · ⬇ CSV · JSON

Score

Rank	Model	Score	Best Score	Return	Paper	Code	Year
49	Rational DQN Average	650	–	–	Adaptive Rational Activations to Boost Deep Reinforcement Learning	ml-research/rational_activations · ml-research/rational_rl · k4ntz/activation-functions · +1	2021
52	SARSA	267.9	–	–
53	Best Learner	250.1	–	–	The Arcade Learning Environment: An Evaluation Platform for General Agents	mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory	2012
54	SAC	160.8	–	–	Soft Actor-Critic for Discrete Action Settings	p-christ/Deep-Reinforcement-Learning-Algorithms-with-PyTorch · ku2482/sac-discrete.pytorch · keraJLi/rejax · +10	2019
55	IQ-Learn	–	–	507	IQ-Learn: Inverse soft-Q Learning for Imitation	Div99/IQ-Learn · robfiras/ls-iq · google-deepmind/csil · +2	2021
56	GDI-H3(200M frames)	154380	–	–	Generalized Data Distribution Iteration		2022
56	GDI-H3	154380	–	–	Generalized Data Distribution Iteration		2022
58	GDI-I3	140460	–	–	Generalized Data Distribution Iteration		2022
58	GDI-I3	140460	–	–	GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning		2021
60	MuZero	74335.30	–	–	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model	werner-duvaud/muzero-general · opendilab/LightZero · koulanurag/muzero-pytorch · +15	2019
61	Ape-X	54681	–	–	Distributed Prioritized Experience Replay	ray-project/ray · vwxyzjn/cleanrl · opendilab/DI-engine · +12	2018
62	Agent57	48680.86	–	–	Agent57: Outperforming the Atari Human Benchmark	michaelnny/deep_rl_zoo · pocokhc/agent57 · yuta0821/agent57_pytorch · +2	2020
63	FQF	46498.3	–	–	Fully Parameterized Quantile Function for Distributional Reinforcement Learning	opendilab/DI-engine · ku2482/fqf-iqn-qrdqn.pytorch · ku2482/rljax · +3	2019
64	IMPALA (deep)	43595.78	–	–	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	ray-project/ray · opendilab/DI-engine · deepmind/haiku · +21	2018
65	R2D2	43223.4	–	–	Recurrent Experience Replay in Distributed Reinforcement Learning	opendilab/DI-engine · michaelnny/deep_rl_zoo · garymm/earl	2019
66	IQN	28888	–	–	Implicit Quantile Networks for Distributional Reinforcement Learning	opendilab/DI-engine · chainer/chainerrl · Kchu/DeepRL_CK · +16	2018
67	A3C LSTM hs	23846.0	–	–	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
68	ASL DDQN	21602	–	–	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	xinjinghao/color	2023
69	QR-DQN-1	20972	–	–	Distributional Reinforcement Learning with Quantile Regression	DLR-RM/stable-baselines3 · facebookresearch/Horizon · facebookresearch/ReAgent · +14	2017
70	A3C FF hs	15730.5	–	–	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
71	Prior+Duel noop	15311.5	–	–	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
72	Rainbow	12629.0	–	–	Rainbow: Combining Improvements in Deep Reinforcement Learning	thu-ml/tianshou · facebookresearch/ReAgent · facebookresearch/Horizon · +31	2017
73	Prior+Duel hs	8978.0	–	–	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
74	Duel noop	6427.3	–	–	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
75	Duel hs	5993.1	–	–	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
76	NoisyNet-Dueling	5909	–	–	Noisy Networks for Exploration	opendilab/DI-engine · Curt-Park/rainbow-is-all-you-need · chainer/chainerrl · +12	2017
77	C51 noop	5747.0	–	–	A Distributional Perspective on Reinforcement Learning	facebookresearch/Horizon · facebookresearch/ReAgent · opendilab/DI-engine · +19	2017
78	Prior hs	3912.1	–	–	Prioritized Experience Replay	labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74	2015
79	MuZero (Res2 Adam)	3645.63	–	–	Online and Offline Reinforcement Learning by Planning with a Learned Model	DHDev0/Muzero-unplugged · enpasos/muzero	2021
80	Advantage Learning	3460.79	–	–	Increasing the Action Gap: New Operators for Reinforcement Learning	janhuenermann/neurojs · chainer/chainerrl	2015
81	Persistent AL	3277.59	–	–	Increasing the Action Gap: New Operators for Reinforcement Learning	janhuenermann/neurojs · chainer/chainerrl	2015
82	A2C + SIL	2951.7	–	–	Self-Imitation Learning	junhyukoh/self-imitation-learning · rwightman/pytorch-opensim-rl · SeungeonBaek/continuous-agents-test · +1	2018
83	Bootstrapped DQN	2893	–	–	Deep Exploration via Bootstrapped DQN	tensorflow/models · tensorflow/models · NervanaSystems/coach · +3	2016
84	Prior noop	2865.8	–	–	Prioritized Experience Replay	labmlai/annotated_deep_learning_paper_implementations · hill-a/stable-baselines · NervanaSystems/coach · +74	2015
85	DNA	2731	–	–	DNA: Proximal Policy Optimization with a Dual Network Architecture	maitchison/PPO	2022
86	UCT	2718	–	–	The Arcade Learning Environment: An Evaluation Platform for General Agents	mgbellemare/Arcade-Learning-Environment · kenjyoung/MinAtar · nandomp/AICollaboratory	2012
87	DDQN (tuned) hs	2628.7	–	–	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
88	DDQN+Pop-Art noop	2589.7	–	–	Learning values across many orders of magnitude		2016
89	DDQN (tuned) noop	2525.5	–	–	Dueling Network Architectures for Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · facebookresearch/Horizon · +70	2015
90	DreamerV2	2474	–	–	Mastering Atari with Discrete World Models	opendilab/DI-engine · danijar/dreamerv2 · andrejorsula/drl_grasping · +6	2020
91	A3C FF (1 day) hs	2214.7	–	–	Asynchronous Methods for Deep Reinforcement Learning	ray-project/ray · DLR-RM/stable-baselines3 · tensorpack/tensorpack · +67	2016
92	MFEC	1990	2490	–	Model-Free Episodic Control with State Aggregation		2020
93	Nature DQN	1976.0	–	–	Human level control through deep reinforcement learning	MaximeVandegar/Papers-in-100-Lines-of-Code · gordicaleksa/pytorch-learn-reinforcement-learning · xiuyu0000/new_papers_codes · +5	2015
94	DQN noop	1692.3	–	–	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
95	Recurrent Rational DQN Average	1395	–	–	Adaptive Rational Activations to Boost Deep Reinforcement Learning	ml-research/rational_activations · ml-research/rational_rl · k4ntz/activation-functions · +1	2021
96	DQN hs	1293.8	–	–	Deep Reinforcement Learning with Double Q-learning	labmlai/annotated_deep_learning_paper_implementations · tensorpack/tensorpack · hill-a/stable-baselines · +94	2015
97	POP3D	1216.15	–	–	Policy Optimization With Penalized Point Probability Distance: An Alternative To Proximal Policy Optimization	cxxgtxy/POP3D · paperwithcode/pop3d	2018
98	Gorila	1183.3	–	–	Massively Parallel Methods for Deep Reinforcement Learning	nandomp/AICollaboratory · londoed/Kortex · londoed/Gorila	2015
99	MAC	1173.1	–	–	Mean Actor Critic	kavosh8/MAC · camall3n/atari-MAC	2017
100	DQN Best	1075	–	–	Playing Atari with Deep Reinforcement Learning	labmlai/annotated_deep_learning_paper_implementations · ray-project/ray · DLR-RM/stable-baselines3 · +109	2013