Search Results for author:
Found 19 papers, 9 papers with code
MuJoCo MPC for Humanoid Control: Evaluation on HumanoidBench
We tackle the recently introduced benchmark for whole-body humanoid control HumanoidBench using MuJoCo MPC.
Adaptive $Q$-Network: On-the-fly Target Selection for Deep Reinforcement Learning
Deep Reinforcement Learning (RL) is well known for being highly sensitive to hyperparameters, requiring practitioners substantial efforts to optimize them for the problem at hand.
What Matters for Active Texture Recognition With Vision-Based Tactile Sensors
By evaluating our method on a previously published Active Clothing Perception Dataset and on a real robotic system, we establish that the choice of the active exploration strategy has only a minor influence on the recognition accuracy, whereas data augmentation and dropout rate play a significantly larger role.
Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning
It has been observed that this scheme can be potentially generalized to carry out multiple iterations of the Bellman operator at once, benefiting the underlying learning algorithm.
Parameterized Projected Bellman Operator
We formulate an optimization problem to learn PBO for generic sequential decision-making problems, and we theoretically analyze its properties in two representative classes of RL problems.
How Crucial is Transformer in Decision Transformer?
On the other hand, the proposed Decision LSTM is able to achieve expert-level performance on these tasks, in addition to learning a swing-up controller on the real system.
Active Exploration for Robotic Manipulation
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in recent years.
Active Inference for Robotic Manipulation
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in the last decades.
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.
Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative Entropy Trust-Regions
Trajectory optimization and model predictive control are essential techniques underpinning advanced robotic applications, ranging from autonomous driving to full-body humanoid control.
A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning
Across machine learning, the use of curricula has shown strong empirical potential to improve learning from data by avoiding local optima of training objectives.
Receding Horizon Curiosity
Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion.
Self-Paced Contextual Reinforcement Learning
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots.
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.
Entropic Regularization of Markov Decision Processes
An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration.
Entropic Risk Measure in Policy Search
With the increasing pace of automation, modern robotic systems need to act in stochastic, non-stationary, partially observable environments.
CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
Sample efficiency is a crucial problem in deep reinforcement learning.
f-Divergence constrained policy improvement
We carry out asymptotic analysis of the solutions for different values of $\alpha$ and demonstrate the effects of using different divergence functions on a multi-armed bandit problem and on common standard reinforcement learning problems.
Catching heuristics are optimal control policies
In this paper, we show that interception strategies appearing to be heuristics can be understood as computational solutions to the optimal control problem faced by a ball-catching agent acting under uncertainty.
