Search Results for author:
Found 144 papers, 47 papers with code
Learning Multimodal Latent Dynamics for Human-Robot Interaction
The generated robot motions are further adapted with Inverse Kinematics to ensure the desired physical proximity with a human, combining the ease of joint space learning and accurate task space reachability.
Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
Multi-Task Reinforcement Learning (MTRL) tackles the long-standing problem of endowing agents with skills that generalize across a variety of problems.
Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks.
Time-Efficient Reinforcement Learning with Stochastic Stateful Policies
Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure.
LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion
Imitation Learning (IL) holds great promise for enabling agile locomotion in embodied agents.
Domain Randomization via Entropy Maximization
Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL).
Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula
To this end, Robust Adversarial Reinforcement Learning (RARL) trains a protagonist against destabilizing forces exercised by an adversary in a competitive zero-sum Markov game, whose optimal solution, i. e., rational strategy, corresponds to a Nash equilibrium.
On the Benefit of Optimal Transport for Curriculum Reinforcement Learning
In this work, we focus on framing curricula as interpolations between task distributions, which has previously been shown to be a viable approach to CRL.
Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning
Reinforcement Learning (RL) allows learning non-trivial robot control laws purely from data.
Sampling-Free Probabilistic Deep State-Space Models
Many real-world dynamical systems can be described as State-Space Models (SSMs).
Value-Distributional Model-Based Reinforcement Learning
We study the problem from a model-based Bayesian reinforcement learning perspective, where the goal is to learn the posterior distribution over value functions induced by parameter (epistemic) uncertainty of the Markov decision process.
Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models
Learning priors on trajectory distributions can help accelerate robot motion planning optimization.
Function-Space Regularization for Deep Bayesian Classification
Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior.
Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems
Furthermore, we propose structured approximations to the covariance matrices of the Gaussian components in order to scale up to systems with many agents.
Model Predictive Control with Gaussian-Process-Supported Dynamical Constraints for Autonomous Vehicles
We propose a model predictive control approach for autonomous vehicles that exploits learned Gaussian processes for predicting human driving behavior.
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.
LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning
Recent methods for imitation learning directly learn a $Q$-function using an implicit reward formulation rather than an explicit reward function.
A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors
Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment.
Model-Based Uncertainty in Value Functions
We consider the problem of quantifying uncertainty over expected cumulative rewards in model-based reinforcement learning.
Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks
Motion planning is a mature area of research in robotics with many well-established methods based on optimization or sampling the state space, suitable for solving kinematic motion planning.
Information-Theoretic Safe Exploration with Gaussian Processes
We consider a sequential decision making task where we are not allowed to evaluate parameters that violate an a priori unknown (safety) constraint.
Hierarchical Policy Blending As Optimal Transport
We present hierarchical policy blending as optimal transport (HiPBOT).
PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison
On the one hand, we found that PAC-Bayes bounds are a useful tool for designing offline bandit algorithms with performance guarantees.
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.
Variational Hierarchical Mixtures for Probabilistic Learning of Inverse Dynamics
We derive two efficient variational inference techniques to learn these representations and highlight the advantages of hierarchical infinite local regression models, such as dealing with non-smooth functions, mitigating catastrophic forgetting, and enabling parameter sharing and fast predictions.
Active Exploration for Robotic Manipulation
Robotic manipulation stands as a largely unsolved problem despite significant advances in robotics and machine learning in recent years.
MILD: Multimodal Interactive Latent Dynamics for Learning Human-Robot Interaction
Modeling interaction dynamics to generate robot trajectories that enable a robot to adapt and react to a human's actions and intentions is critical for efficient and effective collaborative Human-Robot Interactions (HRI).
Hierarchical Policy Blending as Inference for Reactive Robot Control
To combine the benefits of reactive policies and planning, we propose a hierarchical motion generation method.
Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes
Monte Carlo methods have become increasingly relevant for control of non-differentiable systems, approximate dynamics models and learning from data.
Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction
Our proposed approach achieves state-of-the-art performance in simulated high-dimensional and dynamic tasks while avoiding collisions with the environment.
Self-supervised Sequential Information Bottleneck for Robust Exploration in Deep Reinforcement Learning
Recent works based on state-visitation counts, curiosity and entropy-maximization generate intrinsic reward signals to motivate the agent to visit novel states for exploration.
Structured Q-learning For Antibody Design
Optimizing combinatorial structures is core to many real-world problems, such as those encountered in life sciences.
SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion
In this work, we focus on learning SE(3) diffusion models for 6DoF grasping, giving rise to a novel framework for joint grasp and motion optimization without needing to decouple grasp selection from trajectory generation.
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.
Learning Implicit Priors for Motion Optimization
In this paper, we focus on the problem of integrating Energy-based Models (EBM) as guiding priors for motion optimization.
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.
Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking
Task and Motion Planning (TAMP) provides a hierarchical framework to handle the sequential nature of manipulation tasks by interleaving a symbolic task planner that generates a possible action sequence, with a motion planner that checks the kinematic feasibility in the geometric world, generating robot trajectories if several constraints are satisfied, e. g., a collision-free trajectory from one state to another.
Regularized Deep Signed Distance Fields for Reactive Motion Generation
Autonomous robots should operate in real-world dynamic environments and collaborate with humans in tight spaces.
Dimensionality Reduction and Prioritized Exploration for Policy Search
Black-box policy optimization is a class of reinforcement learning algorithms that explores and updates the policies at the parameter level.
An Analysis of Measure-Valued Derivatives for Policy Gradients
This estimator is unbiased, has low variance, and can be used with differentiable and non-differentiable function approximators.
Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery
Robot assembly discovery is a challenging problem that lives at the intersection of resource allocation and motion planning.
Robot Learning of Mobile Manipulation with Reachability Behavior Priors
Finally, we zero-transfer our learned 6D fetching policy with BHyRL to our MM robot TIAGo++.
PAC-Bayesian Lifelong Learning For Multi-Armed Bandits
We present a PAC-Bayesian analysis of lifelong learning.
An Adaptive Human Driver Model for Realistic Race Car Simulations
This work contributes to a better understanding and modeling of the human driver, aiming to expedite simulation methods in the modern vehicle development process and potentially supporting automated driving and racing technologies.
Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images
Recent methods for reinforcement learning from images use auxiliary tasks to learn image features that are used by the agent's policy or Q-function.
A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search
In this work, we propose two methods for improving the convergence rate and exploration based on a newly introduced backup operator and entropy regularization.
Distilled Domain Randomization
However, these methods are notorious for the enormous amount of required training data which is prohibitively expensive to collect on real robots.
Model-Based Reinforcement Learning via Stochastic Hybrid Models
Optimal control of general nonlinear systems is a central challenge in automation.
Robot Learning from Randomized Simulations: A Review
The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data.
Learning Stable Vector Fields on Lie Groups
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.
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.
Function-Space Variational Inference for Deep Bayesian Classification
Bayesian deep learning approaches assume model parameters to be latent random variables and infer posterior predictive distributions to quantify uncertainty, increase safety and trust, and prevent overconfident and unpredictable behavior.
Boosted Curriculum Reinforcement Learning
This approach, which we refer to as boosted curriculum reinforcement learning (BCRL), has the benefit of naturally increasing the representativeness of the functional space by adding a new residual each time a new task is presented.
Metrics Matter: A Closer Look on Self-Paced Reinforcement Learning
Experiments demonstrate that the resulting introduction of metric structure into the curriculum allows for a well-behaving non-parametric version of SPRL that leads to stable learning performance across tasks.
An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients
This estimator is unbiased, has low variance, and can be used with differentiable and non-differentiable function approximators.
Exploration via Empowerment Gain: Combining Novelty, Surprise and Learning Progress
We show that while such an agent is still novelty seeking, i. e. interested in exploring the whole state space, it focuses on exploration where its perceived influence is greater, avoiding areas of greater stochasticity or traps that limit its control.
High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning
We introduce a method combining variational autoencoders (VAEs) and deep metric learning to perform Bayesian optimisation (BO) over high-dimensional and structured input spaces.
Ranked #1 on
Molecular Graph Generation
on ZINC
Robust Value Iteration for Continuous Control Tasks
The adversarial perturbations encourage a optimal policy that is robust to changes in the dynamics.
Efficient Stochastic Optimal Control through Approximate Bayesian Input Inference
Optimal control under uncertainty is a prevailing challenge for many reasons.
Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers
A key feature of intelligent behaviour is the ability to learn abstract strategies that scale and transfer to unfamiliar problems.
Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning
Reactive motion generation problems are usually solved by computing actions as a sum of policies.
Value Iteration in Continuous Actions, States and Time
This algorithm enables dynamic programming for continuous states and actions with a known dynamics model.
Reinforcement Learning using Guided Observability
Due to recent breakthroughs, reinforcement learning (RL) has demonstrated impressive performance in challenging sequential decision-making problems.
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.
SKID RAW: Skill Discovery from Raw Trajectories
Integrating robots in complex everyday environments requires a multitude of problems to be solved.
Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning
Substantial advancements to model-based reinforcement learning algorithms have been impeded by the model-bias induced by the collected data, which generally hurts performance.
Model-based Reinforcement Learning
reinforcement-learning
+1
Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk
Discrete-time stochastic optimal control remains a challenging problem for general, nonlinear systems under significant uncertainty, with practical solvers typically relying on the certainty equivalence assumption, replanning and/or extensive regularization.
Extended Tree Search for Robot Task and Motion Planning
Moreover, we effectively combine this skeleton space with the resultant motion variable spaces into a single extended decision space.
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.
Structured Policy Representation: Imposing Stability in arbitrarily conditioned dynamic systems
We present a new family of deep neural network-based dynamic systems.
Perspectives on Sim2Real Transfer for Robotics: A Summary of the R:SS 2020 Workshop
This report presents the debates, posters, and discussions of the Sim2Real workshop held in conjunction with the 2020 edition of the "Robotics: Science and System" conference.
HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation
Our results on the Bayesmark benchmark indicate that heteroscedasticity and non-stationarity pose significant challenges for black-box optimisers.
Ranked #1 on
Hyperparameter Optimization
on Bayesmark
Neural Linear Models with Functional Gaussian Process Priors
Neural linear models (NLM) and Gaussian processes (GP) are both examples of Bayesian linear regression on rich feature spaces.
Convex Optimization with an Interpolation-based Projection and its Application to Deep Learning
We then propose an optimization algorithm that follows the gradient of the composition of the objective and the projection and prove its convergence for linear objectives and arbitrary convex and Lipschitz domain defining inequality constraints.
A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning
Probabilistic regression techniques in control and robotics applications have to fulfill different criteria of data-driven adaptability, computational efficiency, scalability to high dimensions, and the capacity to deal with different modalities in the data.
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
Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient
Off-policy Reinforcement Learning (RL) holds the promise of better data efficiency as it allows sample reuse and potentially enables safe interaction with the environment.
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.
Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills
Parameterized movement primitives have been extensively used for imitation learning of robotic tasks.
ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows
We introduce ImitationFlow, a novel Deep generative model that allows learning complex globally stable, stochastic, nonlinear dynamics.
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.
Differentiable Implicit Layers
In this paper, we introduce an efficient backpropagation scheme for non-constrained implicit functions.
Active Inference or Control as Inference? A Unifying View
Active inference (AI) is a persuasive theoretical framework from computational neuroscience that seeks to describe action and perception as inference-based computation.
Model-Based Quality-Diversity Search for Efficient Robot Learning
One approach that was recently used to autonomously generate a repertoire of diverse skills is a novelty based Quality-Diversity~(QD) algorithm.
Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization
We consider the problem of creating a 3D model using depth images captured by a team of multiple robots.
Convex Regularization in Monte-Carlo Tree Search
Monte-Carlo planning and Reinforcement Learning (RL) are essential to sequential decision making.
A Deterministic Approximation to Neural SDEs
Our deterministic approximation of the transition kernel is applicable to both training and prediction.
Learning to Play Table Tennis From Scratch using Muscular Robots
This work is the first to (a) fail-safe learn of a safety-critical dynamic task using anthropomorphic robot arms, (b) learn a precision-demanding problem with a PAM-driven system despite the control challenges and (c) train robots to play table tennis without real balls.
Continuous Action Reinforcement Learning from a Mixture of Interpretable Experts
Reinforcement learning (RL) has demonstrated its ability to solve high dimensional tasks by leveraging non-linear function approximators.
Orientation Attentive Robotic Grasp Synthesis with Augmented Grasp Map Representation
Inherent morphological characteristics in objects may offer a wide range of plausible grasping orientations that obfuscates the visual learning of robotic grasping.
Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation
The control of nonlinear dynamical systems remains a major challenge for autonomous agents.
Sharing Knowledge in Multi-Task Deep Reinforcement Learning
We study the benefit of sharing representations among tasks to enable the effective use of deep neural networks in Multi-Task Reinforcement Learning.
Self-Paced Deep Reinforcement Learning
Curriculum reinforcement learning (CRL) improves the learning speed and stability of an agent by exposing it to a tailored series of tasks throughout learning.
Deep Reinforcement Learning with Weighted Q-Learning
In this regard, Weighted Q-Learning (WQL) effectively reduces bias and shows remarkable results in stochastic environments.
Learning to Fly via Deep Model-Based Reinforcement Learning
Learning to control robots without requiring engineered models has been a long-term goal, promising diverse and novel applications.
Model-based Reinforcement Learning
reinforcement-learning
+1
Deep Adversarial Reinforcement Learning for Object Disentangling
The ARL framework utilizes an adversary, which is trained to steer the original agent, the protagonist, to challenging states.
Data-efficient Domain Randomization with Bayesian Optimization
Domain randomization methods tackle this problem by randomizing the physics simulator (source domain) during training according to a distribution over domain parameters in order to obtain more robust policies that are able to overcome the reality gap.
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.
Dimensionality Reduction of Movement Primitives in Parameter Space
The empirical analysis shows that the dimensionality reduction in parameter space is more effective than in configuration space, as it enables the representation of the movements with a significant reduction of parameters.
Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms
The development of autonomous robotic systems that can learn from human demonstrations to imitate a desired behavior - rather than being manually programmed - has huge technological potential.
An Upper Bound of the Bias of Nadaraya-Watson Kernel Regression under Lipschitz Assumptions
The Nadaraya-Watson kernel estimator is among the most popular nonparameteric regression technique thanks to its simplicity.
A Probabilistic Framework for Imitating Human Race Driver Behavior
To approach this problem, we propose Probabilistic Modeling of Driver behavior (ProMoD), a modular framework which splits the task of driver behavior modeling into multiple modules.
A Nonparametric Off-Policy Policy Gradient
Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes.
MushroomRL: Simplifying Reinforcement Learning Research
MushroomRL is an open-source Python library developed to simplify the process of implementing and running Reinforcement Learning (RL) experiments.
Long-Term Visitation Value for Deep Exploration in Sparse Reward Reinforcement Learning
Empirical results on classic and novel benchmarks show that the proposed approach outperforms existing methods in environments with sparse rewards, especially in the presence of rewards that create suboptimal modes of the objective function.
Learning Human Postural Control with Hierarchical Acquisition Functions
In order to reach similar performance, we developed a hierarchical Bayesian optimization algorithm that replicates the cognitive inference and memorization process for avoiding failures in motor control tasks.
Generalized Mean Estimation in Monte-Carlo Tree Search
Finally, we empirically demonstrate the effectiveness of our method in well-known MDP and POMDP benchmarks, showing significant improvement in performance and convergence speed w. r. t.
Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer Architecture
A key feature of intelligent behavior is the ability to learn abstract strategies that transfer to unfamiliar problems.
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.
Stochastic Optimal Control as Approximate Input Inference
Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning.
Self-Paced Contextual Reinforcement Learning
Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots.
Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer
A key feature of intelligent behavior is the ability to learn abstract strategies that transfer to unfamiliar problems.
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.
Real Time Trajectory Prediction Using Deep Conditional Generative Models
Our method uses encoder and decoder deep networks that maps complete or partial trajectories to a Gaussian distributed latent space and back, allowing for fast inference of the future values of a trajectory given previous observations.
Model-based Lookahead Reinforcement Learning
Model-based Reinforcement Learning (MBRL) allows data-efficient learning which is required in real world applications such as robotics.
Experience Reuse with Probabilistic Movement Primitives
Accordingly, for learning a new task, time could be saved by restricting the parameter search space by initializing it with the solution of a similar task.
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.
Assessing Transferability from Simulation to Reality for Reinforcement Learning
Optimizing a policy on a slightly faulty simulator can easily lead to the maximization of the `Simulation Optimization Bias` (SOB).
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.
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.
Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction
The approach is evaluated in a collaborative human-robot interaction task with a 7-DoF robot arm.
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.
Switching Linear Dynamics for Variational Bayes Filtering
System identification of complex and nonlinear systems is a central problem for model predictive control and model-based reinforcement learning.
Learning walk and trot from the same objective using different types of exploration
In quadruped gait learning, policy search methods that scale high dimensional continuous action spaces are commonly used.
Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots
High-speed and high-acceleration movements are inherently hard to control.
Information Gathering in Decentralized POMDPs by Policy Graph Improvement
Decentralized policies for information gathering are required when multiple autonomous agents are deployed to collect data about a phenomenon of interest without the ability to communicate.
Was ist eine Professur fuer Kuenstliche Intelligenz?
The Federal Government of Germany aims to boost the research in the field of Artificial Intelligence (AI).
CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
Sample efficiency is a crucial problem in deep reinforcement learning.
Bayesian Online Prediction of Change Points
Online detection of instantaneous changes in the generative process of a data sequence generally focuses on retrospective inference of such change points without considering their future occurrences.
Compatible Natural Gradient Policy Search
Trust-region methods have yielded state-of-the-art results in policy search.
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos
Previously, the exploding gradient problem has been explained to be central in deep learning and model-based reinforcement learning, because it causes numerical issues and instability in optimization.
Model-based Reinforcement Learning
reinforcement-learning
+1
TD-Regularized Actor-Critic Methods
Actor-critic methods can achieve incredible performance on difficult reinforcement learning problems, but they are also prone to instability.
An Algorithmic Perspective on Imitation Learning
This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning.
Adaptation and Robust Learning of Probabilistic Movement Primitives
However, to be able to capture variability and correlations between different joints, a probabilistic movement primitive requires the estimation of a larger number of parameters compared to their deterministic counterparts, that focus on modeling only the mean behavior.
Probabilistic Trajectory Segmentation by Means of Hierarchical Dirichlet Process Switching Linear Dynamical Systems
Using movement primitive libraries is an effective means to enable robots to solve more complex tasks.
Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling
Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention.
Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks
By using learning signals which mimic the intrinsic motivation signalcognitive dissonance in addition with a mental replay strategy to intensify experiences, the stochastic recurrent network can learn from few physical interactions and adapts to novel environments in seconds.
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.
Local Bayesian Optimization of Motor Skills
Bayesian optimization is renowned for its sample efficiency but its application to higher dimensional tasks is impeded by its focus on global optimization.
Policy Search with High-Dimensional Context Variables
A naive application of unsupervised dimensionality reduction methods to the context variables, such as principal component analysis, is insufficient as task-relevant input may be ignored.
Model-Free Trajectory-based Policy Optimization with Monotonic Improvement
In order to show the monotonic improvement of our algorithm, we additionally conduct a theoretical analysis of our policy update scheme to derive a lower bound of the change in policy return between successive iterations.
Manifold Gaussian Processes for Regression
This feature space is often learned in an unsupervised way, which might lead to data representations that are not useful for the overall regression task.
Multi-Task Policy Search
Learning policies that generalize across multiple tasks is an important and challenging research topic in reinforcement learning and robotics.
