Related papers: Mesh-based Tools to Analyze Deep Reinforcement Lea…
The robustness of legged locomotion is crucial for quadrupedal robots in challenging terrains. Recently, Reinforcement Learning (RL) has shown promising results in legged locomotion and various methods try to integrate privileged…
Deep reinforcement learning (deep RL) has emerged as an effective tool for developing controllers for legged robots. However, vanilla deep RL often requires a tremendous amount of training samples and is not feasible for achieving robust…
Model-based reinforcement learning approaches leverage a forward dynamics model to support planning and decision making, which, however, may fail catastrophically if the model is inaccurate. Although there are several existing methods…
Model Predictive Control (MPC) and Reinforcement Learning (RL) are two prominent strategies for controlling legged robots, each with unique strengths. RL learns control policies through system interaction, adapting to various scenarios,…
The use of machine learning to investigate grasp affordances has received extensive attention over the past several decades. The existing literature provides a robust basis to build upon, though a number of aspects may be improved. Results…
This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…
Building robust multimodal models are crucial for achieving reliable deployment in the wild. Despite its importance, less attention has been paid to identifying and improving the robustness of Multimodal Sentiment Analysis (MSA) models. In…
Deep reinforcement learning can generate complex control policies, but requires large amounts of training data to work effectively. Recent work has attempted to address this issue by leveraging differentiable simulators. However, inherent…
Robust Markov decision processes (r-MDPs) extend MDPs by explicitly modelling epistemic uncertainty about transition dynamics. Learning r-MDPs from interactions with an unknown environment enables the synthesis of robust policies with…
Optimal Control for legged robots has gone through a paradigm shift from position-based to torque-based control, owing to the latter's compliant and robust nature. In parallel to this shift, the community has also turned to Deep…
This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world. We present a reinforcement learning framework for training a…
Multi-task learning is a very challenging problem in reinforcement learning. While training multiple tasks jointly allow the policies to share parameters across different tasks, the optimization problem becomes non-trivial: It remains…
This paper focuses on a drag-reducing control strategy on a 2D-simulated laminar flow past a cylinder. Deep reinforcement learning algorithms have been implemented to discover efficient control schemes, using two synthetic jets located on…
This paper concerns the problem of learning control policies for an unknown linear dynamical system to minimize a quadratic cost function. We present a method, based on convex optimization, that accomplishes this task robustly: i.e., we…
Recent studies have demonstrated the immense potential of exploiting muscle actuator morphology for natural and robust movement -- in simulation. A validation on real robotic hardware is yet missing. In this study, we emulate muscle…
Learning-based methods for dexterous manipulation have made notable progress in recent years. However, learned policies often still lack reliability and exhibit limited robustness to important factors of variation. One failure pattern that…
Balancing and push-recovery are essential capabilities enabling humanoid robots to solve complex locomotion tasks. In this context, classical control systems tend to be based on simplified physical models and hard-coded strategies. Although…
We compare the model-free reinforcement learning with the model-based approaches through the lens of the expressive power of neural networks for policies, $Q$-functions, and dynamics. We show, theoretically and empirically, that even for…
Quadrotor stabilizing controllers often require careful, model-specific tuning for safe operation. We use reinforcement learning to train policies in simulation that transfer remarkably well to multiple different physical quadrotors. Our…
Reinforcement learning (RL) policies are prone to high-frequency oscillations, especially undesirable when deploying to hardware in the real-world. In this paper, we identify, categorize, and compare methods from the literature that aim to…