TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Asynchronous Methods for Deep Reinforcement Learning

Asynchronous Methods for Deep Reinforcement Learning

Volodymyr Mnih, Adrià Puigdomènech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, Koray Kavukcuoglu

2016-02-04Reinforcement LearningAtari Gamesreinforcement-learning
PaperPDFCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCodeCode

Abstract

We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-core CPU instead of a GPU. Furthermore, we show that asynchronous actor-critic succeeds on a wide variety of continuous motor control problems as well as on a new task of navigating random 3D mazes using a visual input.

Results

TaskDatasetMetricValueModel
Atari GamesAtari 2600 BoxingScore59.8A3C FF hs
Atari GamesAtari 2600 BoxingScore37.3A3C LSTM hs
Atari GamesAtari 2600 BoxingScore33.7A3C FF (1 day) hs
Atari GamesAtari 2600 Double DunkScore0.1A3C FF (1 day) hs
Atari GamesAtari 2600 Double DunkScore0.1A3C LSTM hs
Atari GamesAtari 2600 Double DunkScore-0.1A3C FF hs
Atari GamesAtari 2600 Ms. PacmanScore850.7A3C LSTM hs
Atari GamesAtari 2600 Ms. PacmanScore653.7A3C FF hs
Atari GamesAtari 2600 Ms. PacmanScore594.4A3C FF (1 day) hs
Atari GamesAtari 2600 CentipedeScore3755.8A3C FF hs
Atari GamesAtari 2600 CentipedeScore3306.5A3C FF (1 day) hs
Atari GamesAtari 2600 CentipedeScore1997A3C LSTM hs
Atari GamesAtari 2600 TutankhamScore156.3A3C FF hs
Atari GamesAtari 2600 TutankhamScore144.2A3C LSTM hs
Atari GamesAtari 2600 TutankhamScore26.1A3C FF (1 day) hs
Atari GamesAtari 2600 FreewayScore0.1A3C FF (1 day) hs
Atari GamesAtari 2600 FreewayScore0.1A3C FF hs
Atari GamesAtari 2600 FreewayScore0.1A3C LSTM hs
Atari GamesAtari 2600 PongScore11.4A3C FF (1 day) hs
Atari GamesAtari 2600 PongScore10.7A3C LSTM hs
Atari GamesAtari 2600 PongScore5.6A3C FF hs
Atari GamesAtari 2600 EnduroScore-82.2A3C FF (1 day) hs
Atari GamesAtari 2600 EnduroScore-82.5A3C FF hs
Atari GamesAtari 2600 EnduroScore-82.5A3C LSTM hs
Atari GamesAtari 2600 KrullScore8066.6A3C FF (1 day) hs
Atari GamesAtari 2600 KrullScore5911.4A3C LSTM hs
Atari GamesAtari 2600 KrullScore5560A3C FF hs
Atari GamesAtari 2600 BreakoutScore766.8A3C LSTM hs
Atari GamesAtari 2600 BreakoutScore681.9A3C FF hs
Atari GamesAtari 2600 BreakoutScore551.6A3C FF (1 day) hs
Atari GamesAtari 2600 FrostbiteScore197.6A3C LSTM hs
Atari GamesAtari 2600 FrostbiteScore190.5A3C FF hs
Atari GamesAtari 2600 FrostbiteScore180.1A3C FF (1 day) hs
Atari GamesAtari 2600 Montezuma's RevengeScore67A3C FF hs
Atari GamesAtari 2600 Montezuma's RevengeScore53A3C FF (1 day) hs
Atari GamesAtari 2600 Montezuma's RevengeScore41A3C LSTM hs
Atari GamesAtari 2600 GopherScore17106.8A3C LSTM hs
Atari GamesAtari 2600 GopherScore10022.8A3C FF hs
Atari GamesAtari 2600 GopherScore8442.8A3C FF (1 day) hs
Atari GamesAtari 2600 Space InvadersScore23846A3C LSTM hs
Atari GamesAtari 2600 Space InvadersScore15730.5A3C FF hs
Atari GamesAtari 2600 Space InvadersScore2214.7A3C FF (1 day) hs
Atari GamesAtari 2600 James BondScore613A3C LSTM hs
Atari GamesAtari 2600 James BondScore541A3C FF hs
Atari GamesAtari 2600 James BondScore351.5A3C FF (1 day) hs
Atari GamesAtari 2600 AmidarScore283.9A3C FF (1 day) hs
Atari GamesAtari 2600 AmidarScore263.9A3C FF hs
Atari GamesAtari 2600 AmidarScore173A3C LSTM hs
Atari GamesAtari 2600 TennisScore-6.3A3C FF hs
Atari GamesAtari 2600 TennisScore-6.4A3C LSTM hs
Atari GamesAtari 2600 TennisScore-10.2A3C FF (1 day) hs
Atari GamesAtari 2600 Crazy ClimberScore138518A3C LSTM hs
Atari GamesAtari 2600 Crazy ClimberScore112646A3C FF hs
Atari GamesAtari 2600 Crazy ClimberScore101624A3C FF (1 day) hs
Atari GamesAtari 2600 AsteroidsScore5093.1A3C LSTM hs
Atari GamesAtari 2600 AsteroidsScore4474.5A3C FF hs
Atari GamesAtari 2600 AsteroidsScore3009.4A3C FF (1 day) hs
Atari GamesAtari 2600 GravitarScore320A3C LSTM hs
Atari GamesAtari 2600 GravitarScore303.5A3C FF hs
Atari GamesAtari 2600 GravitarScore269.5A3C FF (1 day) hs
Atari GamesAtari 2600 Time PilotScore27202A3C LSTM hs
Atari GamesAtari 2600 Time PilotScore12679A3C FF hs
Atari GamesAtari 2600 Time PilotScore5825A3C FF (1 day) hs
Atari GamesAtari 2600 Demon AttackScore115201.9A3C LSTM hs
Atari GamesAtari 2600 Demon AttackScore113308.4A3C FF hs
Atari GamesAtari 2600 Demon AttackScore84997.5A3C FF (1 day) hs
Atari GamesAtari 2600 Battle ZoneScore20760A3C LSTM hs
Atari GamesAtari 2600 Battle ZoneScore12950A3C FF hs
Atari GamesAtari 2600 Battle ZoneScore11340A3C FF (1 day) hs
Atari GamesAtari 2600 Beam RiderScore24622.2A3C LSTM hs
Atari GamesAtari 2600 Beam RiderScore22707.9A3C FF hs
Atari GamesAtari 2600 Beam RiderScore13235.9A3C FF (1 day) hs
Atari GamesAtari 2600 AsterixScore22140.5A3C FF hs
Atari GamesAtari 2600 AsterixScore17244.5A3C LSTM hs
Atari GamesAtari 2600 AsterixScore6723A3C FF (1 day) hs
Atari GamesAtari 2600 Kung-Fu MasterScore40835A3C LSTM hs
Atari GamesAtari 2600 Kung-Fu MasterScore28819A3C FF hs
Atari GamesAtari 2600 Kung-Fu MasterScore3046A3C FF (1 day) hs
Atari GamesAtari 2600 BowlingScore41.8A3C LSTM hs
Atari GamesAtari 2600 BowlingScore36.2A3C FF (1 day) hs
Atari GamesAtari 2600 BowlingScore35.1A3C FF hs
Atari GamesAtari 2600 KangarooScore125A3C LSTM hs
Atari GamesAtari 2600 KangarooScore106A3C FF (1 day) hs
Atari GamesAtari 2600 KangarooScore94A3C FF hs
Atari GamesAtari 2600 AssaultScore14497.9A3C LSTM hs
Atari GamesAtari 2600 AssaultScore5474.9A3C FF hs
Atari GamesAtari 2600 AssaultScore3746.1A3C FF (1 day) hs
Atari GamesAtari 2600 AlienScore945.3A3C LSTM hs
Atari GamesAtari 2600 AlienScore518.4A3C FF hs
Atari GamesAtari 2600 AlienScore182.1A3C FF (1 day) hs
Atari GamesAtari 2600 Fishing DerbyScore22.6A3C LSTM hs
Atari GamesAtari 2600 Fishing DerbyScore18.8A3C FF hs
Atari GamesAtari 2600 Fishing DerbyScore13.6A3C FF (1 day) hs
Atari GamesAtari 2600 SeaquestScore2355.4A3C FF hs
Atari GamesAtari 2600 SeaquestScore2300.2A3C FF (1 day) hs
Atari GamesAtari 2600 SeaquestScore1326.1A3C LSTM hs
Atari GamesAtari 2600 Chopper CommandScore10150A3C LSTM hs
Atari GamesAtari 2600 Chopper CommandScore7021A3C FF hs
Atari GamesAtari 2600 Chopper CommandScore4669A3C FF (1 day) hs
Atari GamesAtari 2600 Video PinballScore470310.5A3C LSTM hs
Atari GamesAtari 2600 Video PinballScore331628.1A3C FF hs
Atari GamesAtari 2600 Video PinballScore185852.6A3C FF (1 day) hs
Atari GamesAtari 2600 Wizard of WorScore18082A3C LSTM hs
Atari GamesAtari 2600 Wizard of WorScore17244A3C FF hs
Atari GamesAtari 2600 Wizard of WorScore5278A3C FF (1 day) hs
Atari GamesAtari 2600 ZaxxonScore24622A3C FF hs
Atari GamesAtari 2600 ZaxxonScore23519A3C LSTM hs
Atari GamesAtari 2600 ZaxxonScore2659A3C FF (1 day) hs
Atari GamesAtari 2600 RobotankScore32.8A3C FF hs
Atari GamesAtari 2600 RobotankScore2.6A3C LSTM hs
Atari GamesAtari 2600 RobotankScore2.3A3C FF (1 day) hs
Atari GamesAtari 2600 Name This GameScore12093.7A3C LSTM hs
Atari GamesAtari 2600 Name This GameScore10476.1A3C FF hs
Atari GamesAtari 2600 Name This GameScore5614A3C FF (1 day) hs
Atari GamesAtari 2600 Star GunnerScore164766A3C LSTM hs
Atari GamesAtari 2600 Star GunnerScore138218A3C FF hs
Atari GamesAtari 2600 Star GunnerScore64393A3C FF (1 day) hs
Atari GamesAtari 2600 Ice HockeyScore-1.7A3C LSTM hs
Atari GamesAtari 2600 Ice HockeyScore-2.8A3C FF hs
Atari GamesAtari 2600 Ice HockeyScore-4.7A3C FF (1 day) hs
Atari GamesAtari 2600 BerzerkScore1433.4A3C FF (1 day) hs
Atari GamesAtari 2600 BerzerkScore862.2A3C LSTM hs
Atari GamesAtari 2600 BerzerkScore817.9A3C FF hs
Atari GamesAtari 2600 AtlantisScore911091A3C FF hs
Atari GamesAtari 2600 AtlantisScore875822A3C LSTM hs
Atari GamesAtari 2600 AtlantisScore772392A3C FF (1 day) hs
Atari GamesAtari 2600 HEROScore32464.1A3C FF hs
Atari GamesAtari 2600 HEROScore28889.5A3C LSTM hs
Atari GamesAtari 2600 HEROScore28765.8A3C FF (1 day) hs
Atari GamesAtari 2600 Bank HeistScore970.1A3C FF hs
Atari GamesAtari 2600 Bank HeistScore946A3C FF (1 day) hs
Atari GamesAtari 2600 Bank HeistScore932.8A3C LSTM hs
Atari GamesAtari 2600 VentureScore25A3C LSTM hs
Atari GamesAtari 2600 VentureScore23A3C FF hs
Atari GamesAtari 2600 VentureScore19A3C FF (1 day) hs
Atari GamesAtari 2600 Private EyeScore421.1A3C LSTM hs
Atari GamesAtari 2600 Private EyeScore206.9A3C FF hs
Atari GamesAtari 2600 Private EyeScore194.4A3C FF (1 day) hs
Atari GamesAtari 2600 Q*BertScore21307.5A3C LSTM hs
Atari GamesAtari 2600 Q*BertScore15148.8A3C FF hs
Atari GamesAtari 2600 Q*BertScore13752.3A3C FF (1 day) hs
Atari GamesAtari 2600 River RaidScore12201.8A3C FF hs
Atari GamesAtari 2600 River RaidScore10001.2A3C FF (1 day) hs
Atari GamesAtari 2600 River RaidScore6591.9A3C LSTM hs
Atari GamesAtari 2600 Road RunnerScore73949A3C LSTM hs
Atari GamesAtari 2600 Road RunnerScore34216A3C FF hs
Atari GamesAtari 2600 Road RunnerScore31769A3C FF (1 day) hs
Atari GamesAtari 2600 Up and DownScore105728.7A3C LSTM hs
Atari GamesAtari 2600 Up and DownScore74705.7A3C FF hs
Atari GamesAtari 2600 Up and DownScore54525.4A3C FF (1 day) hs
Video GamesAtari 2600 BoxingScore59.8A3C FF hs
Video GamesAtari 2600 BoxingScore37.3A3C LSTM hs
Video GamesAtari 2600 BoxingScore33.7A3C FF (1 day) hs
Video GamesAtari 2600 Double DunkScore0.1A3C FF (1 day) hs
Video GamesAtari 2600 Double DunkScore0.1A3C LSTM hs
Video GamesAtari 2600 Double DunkScore-0.1A3C FF hs
Video GamesAtari 2600 Ms. PacmanScore850.7A3C LSTM hs
Video GamesAtari 2600 Ms. PacmanScore653.7A3C FF hs
Video GamesAtari 2600 Ms. PacmanScore594.4A3C FF (1 day) hs
Video GamesAtari 2600 CentipedeScore3755.8A3C FF hs
Video GamesAtari 2600 CentipedeScore3306.5A3C FF (1 day) hs
Video GamesAtari 2600 CentipedeScore1997A3C LSTM hs
Video GamesAtari 2600 TutankhamScore156.3A3C FF hs
Video GamesAtari 2600 TutankhamScore144.2A3C LSTM hs
Video GamesAtari 2600 TutankhamScore26.1A3C FF (1 day) hs
Video GamesAtari 2600 FreewayScore0.1A3C FF (1 day) hs
Video GamesAtari 2600 FreewayScore0.1A3C FF hs
Video GamesAtari 2600 FreewayScore0.1A3C LSTM hs
Video GamesAtari 2600 PongScore11.4A3C FF (1 day) hs
Video GamesAtari 2600 PongScore10.7A3C LSTM hs
Video GamesAtari 2600 PongScore5.6A3C FF hs
Video GamesAtari 2600 EnduroScore-82.2A3C FF (1 day) hs
Video GamesAtari 2600 EnduroScore-82.5A3C FF hs
Video GamesAtari 2600 EnduroScore-82.5A3C LSTM hs
Video GamesAtari 2600 KrullScore8066.6A3C FF (1 day) hs
Video GamesAtari 2600 KrullScore5911.4A3C LSTM hs
Video GamesAtari 2600 KrullScore5560A3C FF hs
Video GamesAtari 2600 BreakoutScore766.8A3C LSTM hs
Video GamesAtari 2600 BreakoutScore681.9A3C FF hs
Video GamesAtari 2600 BreakoutScore551.6A3C FF (1 day) hs
Video GamesAtari 2600 FrostbiteScore197.6A3C LSTM hs
Video GamesAtari 2600 FrostbiteScore190.5A3C FF hs
Video GamesAtari 2600 FrostbiteScore180.1A3C FF (1 day) hs
Video GamesAtari 2600 Montezuma's RevengeScore67A3C FF hs
Video GamesAtari 2600 Montezuma's RevengeScore53A3C FF (1 day) hs
Video GamesAtari 2600 Montezuma's RevengeScore41A3C LSTM hs
Video GamesAtari 2600 GopherScore17106.8A3C LSTM hs
Video GamesAtari 2600 GopherScore10022.8A3C FF hs
Video GamesAtari 2600 GopherScore8442.8A3C FF (1 day) hs
Video GamesAtari 2600 Space InvadersScore23846A3C LSTM hs
Video GamesAtari 2600 Space InvadersScore15730.5A3C FF hs
Video GamesAtari 2600 Space InvadersScore2214.7A3C FF (1 day) hs
Video GamesAtari 2600 James BondScore613A3C LSTM hs
Video GamesAtari 2600 James BondScore541A3C FF hs
Video GamesAtari 2600 James BondScore351.5A3C FF (1 day) hs
Video GamesAtari 2600 AmidarScore283.9A3C FF (1 day) hs
Video GamesAtari 2600 AmidarScore263.9A3C FF hs
Video GamesAtari 2600 AmidarScore173A3C LSTM hs
Video GamesAtari 2600 TennisScore-6.3A3C FF hs
Video GamesAtari 2600 TennisScore-6.4A3C LSTM hs
Video GamesAtari 2600 TennisScore-10.2A3C FF (1 day) hs
Video GamesAtari 2600 Crazy ClimberScore138518A3C LSTM hs
Video GamesAtari 2600 Crazy ClimberScore112646A3C FF hs
Video GamesAtari 2600 Crazy ClimberScore101624A3C FF (1 day) hs
Video GamesAtari 2600 AsteroidsScore5093.1A3C LSTM hs
Video GamesAtari 2600 AsteroidsScore4474.5A3C FF hs
Video GamesAtari 2600 AsteroidsScore3009.4A3C FF (1 day) hs
Video GamesAtari 2600 GravitarScore320A3C LSTM hs
Video GamesAtari 2600 GravitarScore303.5A3C FF hs
Video GamesAtari 2600 GravitarScore269.5A3C FF (1 day) hs
Video GamesAtari 2600 Time PilotScore27202A3C LSTM hs
Video GamesAtari 2600 Time PilotScore12679A3C FF hs
Video GamesAtari 2600 Time PilotScore5825A3C FF (1 day) hs
Video GamesAtari 2600 Demon AttackScore115201.9A3C LSTM hs
Video GamesAtari 2600 Demon AttackScore113308.4A3C FF hs
Video GamesAtari 2600 Demon AttackScore84997.5A3C FF (1 day) hs
Video GamesAtari 2600 Battle ZoneScore20760A3C LSTM hs
Video GamesAtari 2600 Battle ZoneScore12950A3C FF hs
Video GamesAtari 2600 Battle ZoneScore11340A3C FF (1 day) hs
Video GamesAtari 2600 Beam RiderScore24622.2A3C LSTM hs
Video GamesAtari 2600 Beam RiderScore22707.9A3C FF hs
Video GamesAtari 2600 Beam RiderScore13235.9A3C FF (1 day) hs
Video GamesAtari 2600 AsterixScore22140.5A3C FF hs
Video GamesAtari 2600 AsterixScore17244.5A3C LSTM hs
Video GamesAtari 2600 AsterixScore6723A3C FF (1 day) hs
Video GamesAtari 2600 Kung-Fu MasterScore40835A3C LSTM hs
Video GamesAtari 2600 Kung-Fu MasterScore28819A3C FF hs
Video GamesAtari 2600 Kung-Fu MasterScore3046A3C FF (1 day) hs
Video GamesAtari 2600 BowlingScore41.8A3C LSTM hs
Video GamesAtari 2600 BowlingScore36.2A3C FF (1 day) hs
Video GamesAtari 2600 BowlingScore35.1A3C FF hs
Video GamesAtari 2600 KangarooScore125A3C LSTM hs
Video GamesAtari 2600 KangarooScore106A3C FF (1 day) hs
Video GamesAtari 2600 KangarooScore94A3C FF hs
Video GamesAtari 2600 AssaultScore14497.9A3C LSTM hs
Video GamesAtari 2600 AssaultScore5474.9A3C FF hs
Video GamesAtari 2600 AssaultScore3746.1A3C FF (1 day) hs
Video GamesAtari 2600 AlienScore945.3A3C LSTM hs
Video GamesAtari 2600 AlienScore518.4A3C FF hs
Video GamesAtari 2600 AlienScore182.1A3C FF (1 day) hs
Video GamesAtari 2600 Fishing DerbyScore22.6A3C LSTM hs
Video GamesAtari 2600 Fishing DerbyScore18.8A3C FF hs
Video GamesAtari 2600 Fishing DerbyScore13.6A3C FF (1 day) hs
Video GamesAtari 2600 SeaquestScore2355.4A3C FF hs
Video GamesAtari 2600 SeaquestScore2300.2A3C FF (1 day) hs
Video GamesAtari 2600 SeaquestScore1326.1A3C LSTM hs
Video GamesAtari 2600 Chopper CommandScore10150A3C LSTM hs
Video GamesAtari 2600 Chopper CommandScore7021A3C FF hs
Video GamesAtari 2600 Chopper CommandScore4669A3C FF (1 day) hs
Video GamesAtari 2600 Video PinballScore470310.5A3C LSTM hs
Video GamesAtari 2600 Video PinballScore331628.1A3C FF hs
Video GamesAtari 2600 Video PinballScore185852.6A3C FF (1 day) hs
Video GamesAtari 2600 Wizard of WorScore18082A3C LSTM hs
Video GamesAtari 2600 Wizard of WorScore17244A3C FF hs
Video GamesAtari 2600 Wizard of WorScore5278A3C FF (1 day) hs
Video GamesAtari 2600 ZaxxonScore24622A3C FF hs
Video GamesAtari 2600 ZaxxonScore23519A3C LSTM hs
Video GamesAtari 2600 ZaxxonScore2659A3C FF (1 day) hs
Video GamesAtari 2600 RobotankScore32.8A3C FF hs
Video GamesAtari 2600 RobotankScore2.6A3C LSTM hs
Video GamesAtari 2600 RobotankScore2.3A3C FF (1 day) hs
Video GamesAtari 2600 Name This GameScore12093.7A3C LSTM hs
Video GamesAtari 2600 Name This GameScore10476.1A3C FF hs
Video GamesAtari 2600 Name This GameScore5614A3C FF (1 day) hs
Video GamesAtari 2600 Star GunnerScore164766A3C LSTM hs
Video GamesAtari 2600 Star GunnerScore138218A3C FF hs
Video GamesAtari 2600 Star GunnerScore64393A3C FF (1 day) hs
Video GamesAtari 2600 Ice HockeyScore-1.7A3C LSTM hs
Video GamesAtari 2600 Ice HockeyScore-2.8A3C FF hs
Video GamesAtari 2600 Ice HockeyScore-4.7A3C FF (1 day) hs
Video GamesAtari 2600 BerzerkScore1433.4A3C FF (1 day) hs
Video GamesAtari 2600 BerzerkScore862.2A3C LSTM hs
Video GamesAtari 2600 BerzerkScore817.9A3C FF hs
Video GamesAtari 2600 AtlantisScore911091A3C FF hs
Video GamesAtari 2600 AtlantisScore875822A3C LSTM hs
Video GamesAtari 2600 AtlantisScore772392A3C FF (1 day) hs
Video GamesAtari 2600 HEROScore32464.1A3C FF hs
Video GamesAtari 2600 HEROScore28889.5A3C LSTM hs
Video GamesAtari 2600 HEROScore28765.8A3C FF (1 day) hs
Video GamesAtari 2600 Bank HeistScore970.1A3C FF hs
Video GamesAtari 2600 Bank HeistScore946A3C FF (1 day) hs
Video GamesAtari 2600 Bank HeistScore932.8A3C LSTM hs
Video GamesAtari 2600 VentureScore25A3C LSTM hs
Video GamesAtari 2600 VentureScore23A3C FF hs
Video GamesAtari 2600 VentureScore19A3C FF (1 day) hs
Video GamesAtari 2600 Private EyeScore421.1A3C LSTM hs
Video GamesAtari 2600 Private EyeScore206.9A3C FF hs
Video GamesAtari 2600 Private EyeScore194.4A3C FF (1 day) hs
Video GamesAtari 2600 Q*BertScore21307.5A3C LSTM hs
Video GamesAtari 2600 Q*BertScore15148.8A3C FF hs
Video GamesAtari 2600 Q*BertScore13752.3A3C FF (1 day) hs
Video GamesAtari 2600 River RaidScore12201.8A3C FF hs
Video GamesAtari 2600 River RaidScore10001.2A3C FF (1 day) hs
Video GamesAtari 2600 River RaidScore6591.9A3C LSTM hs
Video GamesAtari 2600 Road RunnerScore73949A3C LSTM hs
Video GamesAtari 2600 Road RunnerScore34216A3C FF hs
Video GamesAtari 2600 Road RunnerScore31769A3C FF (1 day) hs
Video GamesAtari 2600 Up and DownScore105728.7A3C LSTM hs
Video GamesAtari 2600 Up and DownScore74705.7A3C FF hs
Video GamesAtari 2600 Up and DownScore54525.4A3C FF (1 day) hs

Related Papers

CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning2025-07-18VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning2025-07-17Spectral Bellman Method: Unifying Representation and Exploration in RL2025-07-17Aligning Humans and Robots via Reinforcement Learning from Implicit Human Feedback2025-07-17VAR-MATH: Probing True Mathematical Reasoning in Large Language Models via Symbolic Multi-Instance Benchmarks2025-07-17QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation2025-07-17Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities2025-07-17Autonomous Resource Management in Microservice Systems via Reinforcement Learning2025-07-17