Filetype
Recent methods for imitation learning directly learn a Q-function using an implicit reward formulation rather than an explicit reward function.However, these methods generally require implicit reward regularization to improve stability and often mistreat absorbing states.Previous works show that a squared norm regularization on the implicit reward function is effective, but do not provide a theore
Quadruped robots are currently a widespread platform for robotics research, thanks to powerful Reinforcement Learning controllers and the availability of cheap and robust commercial platforms. However, to broaden the adoption of the technology in the real world, we require robust navigation stacks relying only on low-cost sensors such as depth cameras. This paper presents a first step towards a ro
Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level. This class of algorithms is widely applied in robotics with movement primitives or non-differentiable policies. Furthermore, these approaches are particularly relevant where exploration at the action level could cause actuator damage or other safety issues. H
Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces. A key component for allowing robots to leave structured lab and manufacturing settings is their ability to evaluate online and real-time collisions with the world around them. Distance-based constraints are fundamental for enabling robots to plan their actions and act safely, protecting
Learning robot motions from demonstration requires models able to specify vector fields for the full robot pose when the task is defined in operational space. Recent advances in reactive motion generation have shown that learning adaptive, reactive, smooth, and stable vector fields is possible. However, these approaches define vector fields on a flat Euclidean manifold, while representing vector f
Reinforcement learning with sparse rewards is still an open challenge. Classic methods rely on getting feedback via extrinsic rewards to train the agent, and in situations where this occurs very rarely the agent learns slowly or cannot learn at all. Similarly, if the agent receives also rewards that create suboptimal modes of the objective function, it will likely prematurely stop exploring. More
Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators. However, these successes are mostly achieved by 'black-box' policies in simulated domains. When deploying RL to the real world, several concerns regarding the use of a 'black-box' policy might be raised. In order to make the learned policies more transparent, we
Highly dynamic robotic tasks require high-speed and reactive robots. These tasks are particularly challenging due to the physical constraints, hardware limitations, and the high uncertainty of dynamics and sensor measures. To face these issues, it's crucial to design robotics agents that generate precise and fast trajectories and react immediately to environmental changes. Air hockey is an example
Reinforcement learning methods for robotics are increasingly successful due to the constant development of better policy gradient techniques. A precise (low variance) and accurate (low bias) gradient estimator is crucial to face increasingly complex tasks. Traditional policy gradient algorithms use the likelihood-ratio trick, which is known to produce unbiased but high variance estimates. More mod
Reinforcement learning in robotics is extremely challenging due to many practical issues, including safety, mechanical constraints, and wear and tear. Typically, these issues are not considered in the machine learning literature. One crucial problem in applying reinforcement learning in the real world is Safe Exploration, which requires physical and safety constraints satisfaction throughout the l
MushroomRL is an open-source Python library developed to simplify the process of im- plementing and running Reinforcement Learning (RL) experiments. Compared to other available libraries, MushroomRL has been created with the purpose of providing a com- prehensive and exible framework to minimize the effort in implementing and testing novel RL methodologies. The architecture of MushroomRL is built
We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning. We leverage the assumption that learning from different tasks, sharing common properties, is helpful to generalize the knowledge of them resulting in a more effective feature extraction compared to learning a single task. Intuitively, the resulting s
We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics. Our approach extends the Normalizing Flows framework to learn stable Stochastic Differential Equations. We prove the Lyapunov stability for a class of Stochastic Differential Equations and we propose a learning algorithm to learn them from a set of demonstrated tr
There is an increasing interest in Reinforcement Learning to solve new and more challenging problems, as those emerging in robotics and unmanned autonomous vehicles. To face these complex systems, a hierarchical and multi-scale representation is crucial. This has brought the interest on Hierarchical Deep Reinforcement learning systems. Despite their successful application, Deep Reinforcement Learn
The ability to navigate in an environment is essential to the autonomy of mobile robots and unmanned autonomous vehicles. Informally, path planning computes a collision-free path from a start location to a goal location in a known environment. Computing such paths accounting for the kinematics of the robot is a problem widely addressed in the literature, often focusing on feasibility and optimalit
In the Multiagent Connected Path Planning problem (MCPP), a team of agents moving in a graph-represented environment must plan a set of start-goal joint paths which ensures global connectivity at each time step, under some communication model. The decision version of this problem asking for the existence of a plan that can be executed in at most a given number of steps is claimed to be NP-complete
In many real-world problems stochasticity is a critical issue for the learning process. The sources of stochasticity come from the transition model, the explorative component of the policy or, even worse, from noisy observations of the reward function. For a finite number of samples, traditional Reinforcement Learning (RL) methods provide biased estimates of the action-value function possibly lead
We present a model-free method for solving the Inverse Reinforcement Learning (IRL) problem given a set of trajectories generated by different experts' policies. In many applications, the observed demonstrations are not produced by the same policy. In fact, they may be provided by multiple experts that follow different (but similar) policies or even by the same expert that does not always replicat
Carbon-14 often dominates the effective dose to the public from authorized discharges from Swedish nuclear power plants (NPPs). In contrast to air-borne releases, water-borne discharges of 14C are currently not routinely monitored at Swedish NPPs. We have measured 14C in Fucus spp. (brown algae, used as bioindicators of 14C) in shallow waters at the Swedish west coast from 2020 to 2024. At Ringhal
