A generalized path integral control approach to reinforcement learning
From MaRDI portal
Recommendations
- An introduction to stochastic control theory, path integrals and reinforcement learning
- Adaptive importance sampling for control and inference
- Policy search for motor primitives in robotics
- Efficient sample reuse in policy gradients with parameter-based exploration
- An Incremental Fast Policy Search Using a Single Sample Path
Cited in
(54)- Reinforcement learning with via-point representation
- Preference-based reinforcement learning: a formal framework and a policy iteration algorithm
- A projected primal-dual gradient optimal control method for deep reinforcement learning
- Phase portraits as movement primitives for fast humanoid robot control
- Accelerating reinforcement learning with a directional-Gaussian-smoothing evolution strategy
- Closing the gap: combining task specification and reinforcement learning for compliant vegetable cutting
- Optimization of market stochastic dynamics
- A survey of inverse reinforcement learning: challenges, methods and progress
- Stochastic differential games: a sampling approach via FBSDEs
- Kernel dynamic policy programming: applicable reinforcement learning to robot systems with high dimensional states
- An active exploration method for data efficient reinforcement learning
- Path-integral-based reinforcement learning algorithm for goal-directed locomotion of snake-shaped robot
- An introduction to stochastic control theory, path integrals and reinforcement learning
- Provably efficient learning with typed parametric models
- Adaptive importance sampling for control and inference
- Action selection in growing state spaces: control of network structure growth
- Hierarchical relative entropy policy search
- Probabilistic inference for determining options in reinforcement learning
- Active inference and agency: optimal control without cost functions
- Learning omnidirectional path following using dimensionality reduction
- Closed-loop learning of visual control policies
- Policy search for motor primitives in robotics
- scientific article; zbMATH DE number 6982305 (Why is no real title available?)
- Nonlinear stochastic receding horizon control: stability, robustness and Monte Carlo methods for control approximation
- Autonomous reinforcement learning with experience replay
- Applications of variable discounting dynamic programming to iterated function systems and related problems
- Using simulation to improve sample-efficiency of Bayesian optimization for bipedal robots
- Non-parametric policy search with limited information loss
- scientific article; zbMATH DE number 7370547 (Why is no real title available?)
- Efficient actor-critic reinforcement learning with embodiment of muscle tone for posture stabilization of the human arm
- Whence the expected free energy?
- Jointly learning environments and control policies with projected stochastic gradient ascent
- scientific article; zbMATH DE number 7626721 (Why is no real title available?)
- A stochastic trust-region framework for policy optimization
- A novel online gait optimization approach for biped robots with point-feet
- Adaptive smoothing for path integral control
- Numerical trajectory optimization for stochastic mechanical systems
- Iterative path integral approach to nonlinear stochastic optimal control under compound Poisson noise
- Integrating a partial model into model free reinforcement learning
- Adaptive path-integral autoencoder: representation learning and planning for dynamical systems
- A multilevel approach for stochastic nonlinear optimal control
- PI-ELM: reinforcement learning-based adaptable policy improvement for dynamical system
- Incremental nonlinear stability analysis of stochastic systems perturbed by Lévy noise
- Optimistic reinforcement learning by forward Kullback-Leibler divergence optimization
- Variational policy search using sparse Gaussian process priors for learning multimodal optimal actions
- A stochastic maximum principle approach for reinforcement learning with parameterized environment
- Deep reinforcement learning in finite-horizon to explore the most probable transition pathway
- Predictive control of linear discrete-time Markovian jump systems by learning recurrent patterns
- Policy iteration reinforcement learning-based control using a grey wolf optimizer algorithm
- Empirical prior based probabilistic inference neural network for policy learning
- Deep ensemble reinforcement learning with multiple deep deterministic policy gradient algorithm
- Optimal consensus control for input-delay nonlinear multi-agent systems with input saturation utilizing synchronous integral reinforcement learning
- Path integral control of partially observed systems via fully observable control approximations
- Leveraging probabilistic optimal control for efficient trajectory optimization
This page was built for publication: A generalized path integral control approach to reinforcement learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2896181)
