paper-with-me

Papers

Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State Domains

2010-12-01 · NeurIPS 2010 12 · Martha White, Adam White

The reinforcement learning community has explored many approaches to obtain- ing value estimates and models to guide decision making; these approaches, how- ever, do not usually provide a measure of confidence in the estimate. Accurate estimates of an agent’s confidence are useful for many applications, such as bi- asing exploration and automatically adjusting parameters to reduce dependence on parameter-tuning. Computing confidence intervals on reinforcement learning value estimates, however, is challenging because data generated by the agent- environment interaction rarely satisfies traditional assumptions. Samples of value- estimates are dependent, likely non-normally distributed and often limited, partic- ularly in early learning when confidence estimates are pivotal. In this work, we investigate how to compute robust confidences for value estimates in continuous Markov decision processes. We illustrate how to use bootstrapping to compute confidence intervals online under a changing policy (previously not possible) and prove validity under a few reasonable assumptions. We demonstrate the applica- bility of our confidence estimation algorithms with experiments on exploration, parameter estimation and tracking.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Makingparameter estimationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Continuous Control with Coarse-to-fine Reinforcement Learning

2024-07-10 · Younggyo Seo, Jafar Uruç, Stephen James

Despite recent advances in improving the sample-efficiency of reinforcement learning (RL) algorithms, designing an RL algorithm that can be practically deployed in real-world environments remains a challenge. In this pap…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+1

Dynamic Interval Restrictions on Action Spaces in Deep Reinforcement Learning for Obstacle Avoidance

2023-06-13 · Tim Grams

Deep reinforcement learning algorithms typically act on the same set of actions. However, this is not sufficient for a wide range of real-world applications where different subsets are available at each step. In this the…

Deep Reinforcement Learningreinforcement-learningReinforcement Learning

Parameter-free Reduction of the Estimation Bias in Deep Reinforcement Learning for Deterministic Policy Gradients

2021-09-24 · Baturay Saglam, Furkan Burak Mutlu, Dogan Can Cicek, Suleyman Serdar Kozat

Approximation of the value functions in value-based deep reinforcement learning induces overestimation bias, resulting in suboptimal policies. We show that when the reinforcement signals received by the agents have a hig…

continuous-controlContinuous ControlDeep Reinforcement LearningMuJoCo+2

Neural Laplace Control for Continuous-time Delayed Systems

2023-02-24 · Samuel Holt, Alihan Hüyük, Zhaozhi Qian, Hao Sun 외

Many real-world offline reinforcement learning (RL) problems involve continuous-time environments with delays. Such environments are characterized by two distinctive features: firstly, the state x(t) is observed at irreg…

Model Predictive ControlOffline RLReinforcement Learning (RL)

Exploiting Estimation Bias in Clipped Double Q-Learning for Continous Control Reinforcement Learning Tasks

2024-02-14 · Niccolò Turcato, Alberto Sinigaglia, Alberto Dalla Libera, Ruggero Carli 외

Continuous control Deep Reinforcement Learning (RL) approaches are known to suffer from estimation biases, leading to suboptimal policies. This paper introduces innovative methods in RL, focusing on addressing and exploi…

Computational Efficiencycontinuous-controlContinuous ControlDeep Reinforcement Learning+2