Search Results for author:
Found 7 papers, 1 papers with code
Transferable Latent-to-Latent Locomotion Policy for Efficient and Versatile Motion Control of Diverse Legged Robots
We validate our approach through extensive simulations and real-world experiments, demonstrating that the pretrained latent-to-latent locomotion policy effectively generalizes to new robot entities and tasks with improved efficiency.
Predictive Lagrangian Optimization for Constrained Reinforcement Learning
And we prove that the resulting optimal policy, achieved through alternating MFOCP and MGPL, aligns with the solution of the primal constrained RL problem, thereby establishing our equivalence framework.
An Explicit Discrete-Time Dynamic Vehicle Model with Assured Numerical Stability
Subsequent to the validation process, we conduct comprehensive simulations comparing our proposed model with both kinematic models and existing dynamic models discretized through the forward Euler method.
Rocket Landing Control with Random Annealing Jump Start Reinforcement Learning
Our approach, called Random Annealing Jump Start (RAJS), is tailored for real-world goal-oriented problems by leveraging prior feedback controllers as guide policy to facilitate environmental exploration and policy learning in RL.
Canonical Form of Datatic Description in Control Systems
This paper for the first time introduces the concept of canonical data form for the purpose of achieving more effective design of datatic controllers.
Bridging the Gap between Newton-Raphson Method and Regularized Policy Iteration
We also show that a modified version of regularized policy iteration, i. e., with finite-step policy evaluation, is equivalent to inexact Newton method where the Newton iteration formula is solved with truncated iterations.
Zeroth-Order Actor-Critic: An Evolutionary Framework for Sequential Decision Problems
We propose to use step-wise exploration in parameter space and theoretically derive the zeroth-order policy gradient.
