Papers Model-based Reinforcement Learning
“Model-based Reinforcement Learning” 태그가 달린 논문 708편 · 필터 해제
DreamingV2: Reinforcement Learning with Discrete World Models without Reconstruction
The present paper proposes a novel reinforcement learning method with world models, DreamingV2, a collaborative extension of DreamerV2 and Dreaming. DreamerV2 is a cutting-edge model-based reinforcement learning from pix…
Contrastive LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+1TransDreamer: Reinforcement Learning with Transformer World Models
The Dreamer agent provides various benefits of Model-Based Reinforcement Learning (MBRL) such as sample efficiency, reusable knowledge, and safe planning. However, its world model and policy networks inherit the limitati…
Model-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Should I send this notification? Optimizing push notifications decision making by modeling the future
Most recommender systems are myopic, that is they optimize based on the immediate response of the user. This may be misaligned with the true objective, such as creating long term user satisfaction. In this work we focus …
Decision MakingModel-based Reinforcement LearningRecommendation SystemsReinforcement Learning (RL)Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization
In the sequential decision making setting, an agent aims to achieve systematic generalization over a large, possibly infinite, set of environments. Such environments are modeled as discrete Markov decision processes with…
Decision MakingModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+3Neural NID Rules
Abstract object properties and their relations are deeply rooted in human common sense, allowing people to predict the dynamics of the world even in situations that are novel but governed by familiar laws of physics. Sta…
Common Sense ReasoningGraph Neural NetworkModel-based Reinforcement LearningObject+2Learning by Doing: Controlling a Dynamical System using Causality, Control, and Reinforcement Learning
Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider the problem of learning how to actively pe…
Model-based Reinforcement Learningreinforcement-learningReinforcement Learning (RL)Reward-Respecting Subtasks for Model-Based Reinforcement Learning
To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning has made progress with state abstraction…
Model-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Meta-Learning Hypothesis Spaces for Sequential Decision-making
Obtaining reliable, adaptive confidence sets for prediction functions (hypotheses) is a central challenge in sequential decision-making tasks, such as bandits and model-based reinforcement learning. These confidence sets…
Bayesian OptimizationDecision MakingMeta-LearningModel-based Reinforcement Learning+2Bellman Meets Hawkes: Model-Based Reinforcement Learning via Temporal Point Processes
We consider a sequential decision making problem where the agent faces the environment characterized by the stochastic discrete events and seeks an optimal intervention policy such that its long-term reward is maximized.…
Decision MakingModel-based Reinforcement LearningPoint Processesreinforcement-learning+3Joint Differentiable Optimization and Verification for Certified Reinforcement Learning
In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typica…
Bilevel OptimizationModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+1Physical Derivatives: Computing policy gradients by physical forward-propagation
Model-free and model-based reinforcement learning are two ends of a spectrum. Learning a good policy without a dynamic model can be prohibitively expensive. Learning the dynamic model of a system can reduce the cost of l…
Model-based Reinforcement LearningOpportunities of Hybrid Model-based Reinforcement Learning for Cell Therapy Manufacturing Process Control
Driven by the key challenges of cell therapy manufacturing, including high complexity, high uncertainty, and very limited process observations, we propose a hybrid model-based reinforcement learning (RL) to efficiently g…
Decision MakingModel-based Reinforcement LearningReinforcement Learning (RL)Stochastic OptimizationAssessing Policy, Loss and Planning Combinations in Reinforcement Learning using a New Modular Architecture
The model-based reinforcement learning paradigm, which uses planning algorithms and neural network models, has recently achieved unprecedented results in diverse applications, leading to what is now known as deep reinfor…
Deep Reinforcement LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+1Exponential Family Model-Based Reinforcement Learning via Score Matching
We propose an optimistic model-based algorithm, dubbed SMRL, for finite-horizon episodic reinforcement learning (RL) when the transition model is specified by exponential family distributions with $d$ parameters and the …
Density EstimationModel-based Reinforcement Learningregressionreinforcement-learning+2Exploration-exploitation trade-off for continuous-time episodic reinforcement learning with linear-convex models
We develop a probabilistic framework for analysing model-based reinforcement learning in the episodic setting. We then apply it to study finite-time horizon stochastic control problems with linear dynamics but unknown co…
Model-based Reinforcement LearningReinforcement Learning (RL)CEM-GD: Cross-Entropy Method with Gradient Descent Planner for Model-Based Reinforcement Learning
Current state-of-the-art model-based reinforcement learning algorithms use trajectory sampling methods, such as the Cross-Entropy Method (CEM), for planning in continuous control settings. These zeroth-order optimizers r…
continuous-controlContinuous ControlModel-based Reinforcement LearningMuJoCo+1An Experimental Design Perspective on Model-Based Reinforcement Learning
In many practical applications of RL, it is expensive to observe state transitions from the environment. For example, in the problem of plasma control for nuclear fusion, computing the next state for a given state-action…
continuous-controlContinuous ControlExperimental DesignModel-based Reinforcement Learning+3Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Using a model of the environment and a value function, an agent can construct many estimates of a state's value, by unrolling the model for different lengths and bootstrapping with its value function. Our key insight is …
Model-based Reinforcement LearningRolling Shutter CorrectionED2: Environment Dynamics Decomposition World Models for Continuous Control
Model-based reinforcement learning (MBRL) achieves significant sample efficiency in practice in comparison to model-free RL, but its performance is often limited by the existence of model prediction error. To reduce the …
continuous-controlContinuous ControlModel-based Reinforcement LearningSample Complexity of Robust Reinforcement Learning with a Generative Model
The Robust Markov Decision Process (RMDP) framework focuses on designing control policies that are robust against the parameter uncertainties due to the mismatches between the simulator model and real-world settings. An …
Model-based Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)