Reinforcement Learning in Continuous State and Action Spaces

@inproceedings{Hasselt2012ReinforcementLI,
  title={Reinforcement Learning in Continuous State and Action Spaces},
  author={Hado Philip van Hasselt},
  booktitle={Reinforcement Learning},
  year={2012}
}
  • Hado Philip van Hasselt
  • Published in Reinforcement Learning 2012
  • Computer Science
  • Many traditional reinforcement-learning algorithms have been designed for problems with small finite state and action spaces. [...] Key Method We show how to apply these methods to reinforcement-learning problems and discuss many specific algorithms. Amongst others, we cover gradient-based temporal-difference learning, evolutionary strategies, policy-gradient algorithms and (natural) actor-critic methods. We discuss the advantages of different approaches and compare the performance of a state-of-the-art actor…Expand Abstract
    Qualitative Transfer for Reinforcement Learning with Continuous State and Action Spaces
    • 2
    • PDF
    DeepLoco: dynamic locomotion skills using hierarchical deep reinforcement learning
    • 253
    • PDF
    Model-Based Action Exploration
    Off-Policy Neural Fitted Actor-Critic
    • 2
    • Highly Influenced
    • PDF
    Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control
    • 31
    • PDF

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 269 REFERENCES
    Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces
    • 311
    • PDF
    Binary action search for learning continuous-action control policies
    • 40
    • PDF
    Natural actor-critic algorithms
    • 342
    • PDF
    Reinforcement Learning: An Introduction
    • 25,519
    • Highly Influential
    • PDF
    Policy Gradient Methods for Reinforcement Learning with Function Approximation
    • 3,095
    • Highly Influential
    • PDF
    Infinite-Horizon Policy-Gradient Estimation
    • 609
    • PDF
    Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding
    • 1,151
    • PDF
    Reinforcement learning for robots using neural networks
    • 742
    • PDF
    Using continuous action spaces to solve discrete problems
    • 41
    • PDF
    Algorithms for Reinforcement Learning
    • 797
    • Highly Influential
    • PDF