Search Results for author:
Found 13 papers, 6 papers with code
ActSafe: Active Exploration with Safety Constraints for Reinforcement Learning
Under regularity assumptions on the constraints and dynamics, we show that ActSafe guarantees safety during learning while also obtaining a near-optimal policy in finite time.
Transductive Active Learning with Application to Safe Bayesian Optimization
We analyze Safe BO under the lens of a generalization of active learning with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region.
NeoRL: Efficient Exploration for Nonepisodic RL
We study the problem of nonepisodic reinforcement learning (RL) for nonlinear dynamical systems, where the system dynamics are unknown and the RL agent has to learn from a single trajectory, i. e., without resets.
When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL
Finally, we propose OTaCoS, an efficient model-based algorithm for our setting.
Safe Exploration Using Bayesian World Models and Log-Barrier Optimization
A major challenge in deploying reinforcement learning in online tasks is ensuring that safety is maintained throughout the learning process.
Bridging the Sim-to-Real Gap with Bayesian Inference
We present SIM-FSVGD for learning robot dynamics from data.
Active Few-Shot Fine-Tuning
We study the question: How can we select the right data for fine-tuning to a specific task?
Transductive Active Learning: Theory and Applications
We study a generalization of classical active learning to real-world settings with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region.
Data-Efficient Task Generalization via Probabilistic Model-based Meta Reinforcement Learning
We introduce PACOH-RL, a novel model-based Meta-Reinforcement Learning (Meta-RL) algorithm designed to efficiently adapt control policies to changing dynamics.
Tuning Legged Locomotion Controllers via Safe Bayesian Optimization
This paper presents a data-driven strategy to streamline the deployment of model-based controllers in legged robotic hardware platforms.
Hallucinated Adversarial Control for Conservative Offline Policy Evaluation
We study the problem of conservative off-policy evaluation (COPE) where given an offline dataset of environment interactions, collected by other agents, we seek to obtain a (tight) lower bound on a policy's performance.
Gradient-Based Trajectory Optimization With Learned Dynamics
In our hardware experiments, we demonstrate that our learned model can represent complex dynamics for both the Spot and Radio-controlled (RC) car, and gives good performance in combination with trajectory optimization methods.
GoSafeOpt: Scalable Safe Exploration for Global Optimization of Dynamical Systems
Learning optimal control policies directly on physical systems is challenging since even a single failure can lead to costly hardware damage.
