Atari Games On Atari 2600 Ice Hockey

Score

Results

Performance results of various models on this benchmark

Model Name	Score	Paper Title	Repository
Prior+Duel hs	0.5	Deep Reinforcement Learning with Double Q-learning
IMPALA (deep)	3.48	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
DNA	7.2	DNA: Proximal Policy Optimization with a Dual Network Architecture
Nature DQN	-1.6	Human level control through deep reinforcement learning
NoisyNet-Dueling	3	Noisy Networks for Exploration
DQN hs	-1.6	Deep Reinforcement Learning with Double Q-learning
MuZero	67.04	Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
CGP	4	Evolving simple programs for playing Atari games
IQN	0.2	Implicit Quantile Networks for Distributional Reinforcement Learning
GDI-I3	44.94	Generalized Data Distribution Iteration	-
C51 noop	-3.5	A Distributional Perspective on Reinforcement Learning
Best Learner	-9.5	The Arcade Learning Environment: An Evaluation Platform for General Agents
DreamerV2	26	Mastering Atari with Discrete World Models
Agent57	63.64	Agent57: Outperforming the Atari Human Benchmark
A2C + SIL	-2.4	Self-Imitation Learning
QR-DQN-1	-1.7	Distributional Reinforcement Learning with Quantile Regression
A3C LSTM hs	-1.7	Asynchronous Methods for Deep Reinforcement Learning
ASL DDQN	-3.6	Train a Real-world Local Path Planner in One Hour via Partially Decoupled Reinforcement Learning and Vectorized Diversity	-
Prior hs	-0.2	Prioritized Experience Replay
A3C FF (1 day) hs	-4.7	Asynchronous Methods for Deep Reinforcement Learning

0 of 43 row(s) selected.