reinforcement-learning

39 entries in Machine Learning & AI.

• Dyna-QModel-based planning updatesstandardreinforcement-learning
• Prioritized sweeping RLTD-error backup queuespecialistreinforcement-learning
• Monte Carlo controlFirst-visit returnsstandardreinforcement-learning
• Expected SARSAstandalonestandardreinforcement-learning
• Double Q-learningDecoupled max estimatorstandardreinforcement-learning
• Dueling DQNValue-advantage streamsstandardreinforcement-learning
• Prioritized experience replayTD-error samplingstandardreinforcement-learning
• RainbowCombined DQN improvementsspecialistreinforcement-learning
• Distributional RLC51 categorical returnsspecialistreinforcement-learning
• Quantile regression DQNstandalonespecialistreinforcement-learning
• A3CAsynchronous advantage actorsstandardreinforcement-learning
• A2CSynchronous advantage actorsstandardreinforcement-learning
• Generalized advantage estimationLambda-weighted advantagesstandardreinforcement-learning
• DDPGDeterministic actor-criticstandardreinforcement-learning
• TD3Twin critics and delayed updatesstandardreinforcement-learning
• IMPALAV-trace off-policy correctionspecialistreinforcement-learning
• PPGPhasic policy-value trainingspecialistreinforcement-learning
• MuZeroLearned-model tree searchspecialistreinforcement-learning
• AlphaZeroSelf-play policy-value MCTSstandardreinforcement-learning
• World modelsLatent-dynamics rolloutspecialistreinforcement-learning
• DreamerLatent imaginationspecialistreinforcement-learning
• Random network distillationPrediction-error bonusspecialistreinforcement-learning
• Count-based explorationPseudo-count bonusspecialistreinforcement-learning
• Intrinsic curiosity moduleForward-model errorspecialistreinforcement-learning
• Hindsight experience replayGoal relabelingstandardreinforcement-learning
• Conservative Q-learningOut-of-distribution penaltyspecialistreinforcement-learning
• Batch-constrained Q-learningstandalonespecialistreinforcement-learning
• Implicit Q-learningExpectile regressionspecialistreinforcement-learning
• Decision transformerReturn-conditioned sequencesspecialistreinforcement-learning
• Behavior cloningstandalonecanonreinforcement-learning
• DAggerDataset aggregationstandardreinforcement-learning
• GAILAdversarial imitationspecialistreinforcement-learning
• Inverse reinforcement learningMaximum entropyspecialistreinforcement-learning
• MADDPGCentralized critic decentralized actorsspecialistreinforcement-learning
• QMIXMonotonic value mixingspecialistreinforcement-learning
• Successor featuresstandalonespecialistreinforcement-learning
• Option-criticLearned temporal abstractionsspecialistreinforcement-learning
• Feudal networksManager-worker hierarchyspecialistreinforcement-learning
• Reward shapingPotential-based shapingstandardreinforcement-learning