Search Results for author:
Found 14 papers, 7 papers with code
Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning
Therefore, we conclude that the limitation of model-based value expansion methods is not the model accuracy of the learned models.
Revisiting Model-based Value Expansion
Model-based value expansion methods promise to improve the quality of value function targets and, thereby, the effectiveness of value function learning.
Continuous-Time Fitted Value Iteration for Robust Policies
Especially for continuous control, solving this differential equation and its extension the Hamilton-Jacobi-Isaacs equation, is important as it yields the optimal policy that achieves the maximum reward on a give task.
Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models
Especially for learning dynamics models, these black-box models are not desirable as the underlying principles are well understood and the standard deep networks can learn dynamics that violate these principles.
Learning Dynamics Models for Model Predictive Agents
This paper sets out to disambiguate the role of different design choices for learning dynamics models, by comparing their performance to planning with a ground-truth model -- the simulator.
Robust Value Iteration for Continuous Control Tasks
The adversarial perturbations encourage a optimal policy that is robust to changes in the dynamics.
Value Iteration in Continuous Actions, States and Time
This algorithm enables dynamic programming for continuous states and actions with a known dynamics model.
Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning
A limitation of model-based reinforcement learning (MBRL) is the exploitation of errors in the learned models.
Model-based Reinforcement Learning
reinforcement-learning
+1
High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards
Robots that can learn in the physical world will be important to en-able robots to escape their stiff and pre-programmed movements.
A Differentiable Newton Euler Algorithm for Multi-body Model Learning
In this work, we examine a spectrum of hybrid model for the domain of multi-body robot dynamics.
Differential Equations as a Model Prior for Deep Learning and its Applications in Robotics
Therefore, differential equations are a promising approach to incorporate prior knowledge in machine learning models to obtain robust and interpretable models.
HJB Optimal Feedback Control with Deep Differential Value Functions and Action Constraints
The corresponding optimal value function is learned end-to-end by embedding a deep differential network in the Hamilton-Jacobi-Bellmann differential equation and minimizing the error of this equality while simultaneously decreasing the discounting from short- to far-sighted to enable the learning.
Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems
Applying Deep Learning to control has a lot of potential for enabling the intelligent design of robot control laws.
Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning
DeLaN can learn the equations of motion of a mechanical system (i. e., system dynamics) with a deep network efficiently while ensuring physical plausibility.
