Paper tackles zero-shot code feedback using rubric sampling with deep learning.
problem Lack of historical data for supervised learning in introductory programming assignments.
method Human-in-the-loop rubric sampling with deep learning inference.
result Autonomous feedback for first students is more accurate than data-hungry algorithms and approaches human level fidelity.
Method learns from video demonstrations with human feedback.
problem Teaching autonomous agents using video demonstrations and human feedback.
method Constructs a mapping between standard and visual representations using a neural network.
result Effective in teaching a hopper agent to perform a backflip with minimal human feedback.
AutoStan improves Bayesian models via predictive feedback.
problem Improving Bayesian models written in Stan.
method Iterative improvement of Stan models using NLPD and sampler diagnostics feedback.
result AutoStan can autonomously improve diverse Bayesian models across various structures.
Classifier learns to ignore unreliable feedback from end users.
problem Improving classifier performance by filtering unreliable feedback.
method Modeling end users as autonomous agents, periodically retraining classifier with filtered feedback.
result Classifier can identify and filter out unreliable feedback, improving performance.
A method for training autonomous vehicles using continuous human feedback to avoid sub-optimal decisions.
problem Training autonomous vehicles with limited and potentially sub-optimal human demonstrations.
method Continuous scalar feedback for each action to learn from sub-optimal demonstrations and evaluative feedback.
result The proposed method outperforms supervised learning on positive examples alone and learns from sub-optimal demonstrations.
The paper provides guarantees for feedback control with sensor errors.
problem Certifying performance and safety in feedback control systems with sensor errors.
method Solving a supervised learning problem to characterize sensor errors and providing uniform error bounds.
result Finite-time convergence rate on sub-optimality of using a regressor in closed-loop for waypoint tracking.
This research introduces an autonomous robot navigation method using reinforcement learning.
problem Improving robot navigation in complex environments.
method Deep Q Network (DQN) and Proximal Policy Optimization (PPO) models for path planning and decision-making.
result The models enhance robot navigation ability and adaptive learning in unknown environments.
Bayesian optimization identifies optimal alloy formulations.
problem Accelerated discovery in materials science with autonomous systems.
method Bayesian optimization over problem formulation space.
result Framework converges on optimal alloy formulations.
Paper proposes methods to help autonomous vehicles adapt to unexpected driving scenarios.
problem Autonomous vehicles struggle with unexpected driving conditions.
method Robust imitative planning (RIP) and adaptive robust imitative planning (AdaRIP) methods to detect and adapt to distribution shifts.
result Methods outperform current state-of-the-art approaches in nuScenes prediction challenge.
OOM-RL uses financial market losses to align AI agents in autonomous systems.
problem Constrained alignment of autonomous software agents in live financial markets.
method Deploying agents in live financial markets to enforce strict test-driven workflows.
result Final OOM-RL-aligned system achieved a stable equilibrium with an annualized Sharpe ratio of 2.06.
Adaptive vehicle trajectory prediction for safer autonomous driving.
problem Inability of current methods to guarantee physical feasibility and adapt to human driving policies.
method Bayesian recurrent neural network combining policy and physical models, with gradient-based training and parameter adaptation.
result The proposed method ensures physical feasibility and adaptability to human driving policies.
New method learns from subgroup feedback in complex systems.
problem Optimizing complex systems with heterogeneous components.
method Decomposed Gaussian Process (GP) regression and optimization algorithm.
result Proved lower variance and improved accuracy in subgroup feedback.
New approach decouples skill learning and language grounding for autonomous agents.
problem Autonomous acquisition of skills without external instructions and feedback.
method Language-Goal-Behavior (LGB) architecture with semantic representation.
result Decouples skill learning and language grounding, enabling diversity and strategy switching.
Modeling ToM in multi-agent games using adaptive feedback control.
problem Understanding how agents predict and model other agents' mental states in complex interactions.
method Embodied and situated agent models based on distributed adaptive control theory.
result Probabilistic learning agents outperform pure reinforcement-based strategies in game-theoretic tasks.
The problem of optimal switching between nonlinear autonomous subsystems is investigated in this study where the objective is not only bringing the states to close to the desired point, but also adjusting the switching pattern, in the sense of penalizing switching occurrences and assigning different preferences to util…
This paper improves parameter estimation for autonomous systems with unmodeled dynamics.
problem Accurate parameter estimation for risk-aware autonomous systems with unmodeled dynamics.
method Spectral lines-based approach for estimating parameters of dynamic models, allowing deterministic unmodeled dynamics.
result The proposed method leads to non-asymptotic bounds on parameter estimation error, robust to unmodeled dynamics, and matches existing literature in ideal conditions.
This thesis tackles learning reward functions from human comparative feedback.
problem Designing reward functions for complex tasks is challenging and humans often provide suboptimal demonstrations.
method Proposes learning reward functions from comparative feedback (pairwise comparisons, best-of-many choices, rankings, scaled comparisons) and active learning techniques.
result Demonstrates the effectiveness of learning reward functions from comparative feedback in various domains.
ATLAS uses LLMs to adaptively trade by optimizing prompts and coordinating agents.
problem Adapting LLMs for real-time financial decision-making in noisy markets.
method ATLAS integrates structured market data, uses Adaptive-OPRO for prompt optimization, and employs multi-agent coordination.
result Adaptive-OPRO consistently outperforms fixed prompts in financial trading.
Data-efficient reinforcement learning (RL) in continuous state-action spaces using very high-dimensional observations remains a key challenge in developing fully autonomous systems. We consider a particularly important instance of this challenge, the pixels-to-torques problem, where an RL agent learns a closed-loop con…
Study uses deep reinforcement learning for real-time control of nuclear microreactors, achieving similar or superior performance to traditional PID controllers.
problem Minimizing operating costs of nuclear microreactors through autonomous control, especially in load-following scenarios.
method Application of deep reinforcement learning (RL) for real-time drum control in microreactors, using point kinetics model with thermal and xenon feedback.
result Deep reinforcement learning controllers, including single- and multi-agent RL frameworks, can achieve similar or superior load-following performance to traditional PID control across various scenarios.
An assistant learns to mediate decisions between humans and experts, balancing risk and learning.
problem Learning to mediate decisions between imperfect humans and expert knowledge.
method Formalizes online decision mediation, proposes a policy to balance immediate loss and future generalization.
result Consistent gains over benchmarks in decision-making performance.
Deep RL mimics human driving for collision avoidance in self-driving cars.
problem Developing human-like driving policies for autonomous vehicles in mixed traffic environments.
method Model-free, deep reinforcement learning approach using a combination of rule-based and expert-driven data.
result Demonstrated human-like driving policies through Gaussian process modeling of track position and speed distributions.
New algorithm reduces regret in contextual bandits.
problem Minimizing regret in contextual bandits with side information.
method Contextual-Gap algorithm for simple regret minimization.
result Established performance guarantees on simple regret.
This paper discusses how usage patterns and preferences of inhabitants can be learned efficiently to allow smart homes to autonomously achieve energy savings. We propose a frequent sequential pattern mining algorithm suitable for real-life smart home event data. The performance of the proposed algorithm is compared to …
Paper develops rules for autonomous driving using semantic memory.
problem Creating rules for autonomous driving systems.
method Uses real driving data and semantic memory for rule learning.
result Automatic rule learning for autonomous driving.
The study improves deep learning models for safer autonomous vehicles.
problem Robustness of deep neural network models in autonomous driving.
method Analyzes and proposes solutions for deep learning model robustness.
result Enhanced deep learning models for safer autonomous vehicles.
This work improves safety validation of autonomous vehicles by finding interpretable failures.
problem Finding interpretable failures of autonomous systems in simulation.
method Signal temporal logic expressions optimized for high likelihood and human interpretability.
result Our methodology finds more interpretable failures with higher likelihood compared to baseline approaches.
Proves rigidity of 3D partially hyperbolic systems via autonomous dynamics.
problem Rigidity of partially hyperbolic diffeomorphisms in 3D.
method Introducing autonomous dynamical systems to prove rigidity.
result Rigidity of partially hyperbolic diffeomorphisms on 3-manifolds.
New method evaluates AI stock prediction systems based on decision-making processes.
problem Lack of evaluation for AI systems' decision-making processes.
method Scores intermediate decision process using large language models and closed-loop reinforcement learning feedback.
result Composite behavioral score correlates with Sharpe ratio and reduces prediction error.
The paper reviews machine learning safety techniques for autonomous vehicles.
problem Challenges in machine learning safety for autonomous vehicles.
method Organizes practical safety techniques to complement engineering safety.
result Enhances dependability and safety of machine learning algorithms in autonomous vehicles.
Generalizes energy-momentum method for non-autonomous Hamiltonian systems.
problem Stability analysis of non-autonomous Hamiltonian systems with symmetries.
method Develops a new approach to relative equilibrium points and stability conditions for non-autonomous systems.
result Conditions ensuring stability of relative equilibrium points in non-autonomous Hamiltonian systems.
This paper explores formal verification for autonomous systems, identifying limitations and proposing improvements.
problem Ensuring safety of autonomous systems like self-driving cars and drones.
method Formal verification techniques based on formal methods, analyzing three assumptions and their limitations.
result Preliminary work to improve the strength of evidence provided by formal verification.
We enhance autonomous materials research with problem-aware models.
problem Complex decision-making in autonomous materials.
method Bayesian framework, machine learning, physics-based models, operational considerations.
result Improved models reflect problem-specific structure.
The paper explores new risk models for autonomous driving.
problem Risk management and actuarial modeling for autonomous vehicles.
method Examines technical difficulties and proposes a novel risk model.
result The new model better reflects real-world driving safety.
Paper improves autonomous vehicle safety and efficiency with new reinforcement learning methods.
problem Improving robustness and safety in autonomous vehicle control.
method Developed and compared two algorithms: Robust Adversarial Reinforcement Learning and Neural Fictitious Self Play.
result The new algorithms lead to improved driving efficiency and reduced collision rates.
AVs learn from past experiences to improve future performance.
problem Challenging situations and unknown experiences for AVs.
method Transfer Learning and Organic Computing.
result Online Transfer Learning helps update knowledge as tasks evolve.
GOL uses semi-parametric approach to learn from single examples in autonomous driving.
problem Training deep neural networks for autonomous driving requires manual annotation.
method Generative One-Shot Learning (GOL) framework that learns from single examples and regularization samples.
result Generative One-Shot Learning (GOL) generates synthetic data as Pareto optimal solutions.
Paper proposes a method to improve autonomous vehicle performance using synthetically generated images.
problem Limited access to real-world datasets for autonomous vehicle training in countries with scarce data.
method Synthetically generated images to augment and train neural networks on small datasets.
result About 10% improvement in model performance observed.
We prove that the autonomous norm on the group of Hamiltonian diffeomorphisms of the two-dimensional torus is unbounded. We provide explicit examples of Hamiltonian diffeomorphisms with arbitrarily large autonomous norm. For the proofs we construct quasimorphisms on Ham(T2) and some of them are Calabi.
A method predicts driving intentions of human-driven vehicles for safer autonomous driving.
problem Predicting timely driving intentions of human-driven vehicles for autonomous vehicles in mixed traffic.
method A Hidden Markov Model (HMM) approach using continuous mobility features.
result HMMs trained with continuous mobility features improve prediction accuracy.
The study explores autonomous systems and their connections to contact geometry and Frobenius manifolds.
problem Understanding the connections between autonomous systems and geometric structures.
method Investigation of the Darboux-Halphen-Ramanujan system, contact geometry, and Frobenius manifolds.
result Highlighting the role of contact geometry in autonomous systems.
Adaptive framework generates challenging adversarial scenarios for autonomous vehicles.
problem Lack of efficient and adaptable evaluation methods for autonomous vehicles.
method Adaptive evaluation framework using ensemble models and nonparametric Bayesian clustering.
result Adversarial scenarios significantly degrade tested autonomous vehicles' performance.
Improved AST method finds more useful failure scenarios for autonomous vehicles.
problem Finding useful failure scenarios for autonomous vehicle validation is challenging.
method Adaptive Stress Testing with reward augmentation, modified to encode domain information.
result The modified AST method discovers a larger and more expressive subset of failure scenarios.
AI helps build particle physics theories more efficiently.
problem Building viable particle physics theories requires extensive effort and intuition.
method Developed AMBer, a reinforcement learning framework interacting with physics software.
result AMBer constructs viable models with fewer parameters, validating in neutrino theories.
WiseMove framework for safe deep RL in autonomous driving.
problem Ensuring safety in deep reinforcement learning for autonomous driving.
method Modular learning architecture for motion planning.
result Demonstrated on a common traffic scenario, WiseMove supports safe learning.
Safe RL for autonomous vehicles using PCPO with trust regions and parallel learners.
problem Unexplainable behaviours and lack of safety guarantees in RL for real vehicles.
method PCPO framework with trust regions and parallel learners.
result Safe learning confirmed for autonomous vehicles with fast convergence.
Safe reinforcement learning for autonomous vehicles using prediction constraints.
problem Safe reinforcement learning for safety-critical applications like autonomous vehicles.
method Use prediction to constrain exploration in reinforcement learning models.
result Successfully learned intersection handling behaviors on an autonomous vehicle.
ApolloRL offers a platform for RL research in autonomous driving.
problem Improving reinforcement learning for autonomous driving.
method Open platform with training, simulation, and evaluation components.
result Baseline agents perform well in the ApolloRL environment.