Safe Exploration
35 papers with code • 0 benchmarks • 0 datasets
Safe Exploration is an approach to collect ground truth data by safely interacting with the environment.
Source: Chance-Constrained Trajectory Optimization for Safe Exploration and Learning of Nonlinear Systems
Benchmarks
These leaderboards are used to track progress in Safe Exploration
Libraries
Use these libraries to find Safe Exploration models and implementationsMost implemented papers
Safe reinforcement learning for probabilistic reachability and safety specifications: A Lyapunov-based approach
62subinh/deeprl_safety_specification
•
•
Our approach constructs a Lyapunov function with respect to a safe policy to restrain each policy improvement stage.
Curiosity Killed or Incapacitated the Cat and the Asymptotically Optimal Agent
Much work in reinforcement learning uses an ergodicity assumption to avoid this problem.
Enforcing Almost-Sure Reachability in POMDPs
Partially-Observable Markov Decision Processes (POMDPs) are a well-known stochastic model for sequential decision making under limited information.
Verifiably Safe Exploration for End-to-End Reinforcement Learning
We also prove that our method of enforcing the safety constraints preserves all safe policies from the original environment.
Provably Safe PAC-MDP Exploration Using Analogies
A key challenge in applying reinforcement learning to safety-critical domains is understanding how to balance exploration (needed to attain good performance on the task) with safety (needed to avoid catastrophic failure).
Neurosymbolic Reinforcement Learning with Formally Verified Exploration
We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces.
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution
For such complex tasks, the recently proposed RUDDER uses reward redistribution to leverage steps in the Q-function that are associated with accomplishing sub-tasks.
Autonomous UAV Exploration of Dynamic Environments via Incremental Sampling and Probabilistic Roadmap
Autonomous exploration requires robots to generate informative trajectories iteratively.
Safe Continuous Control with Constrained Model-Based Policy Optimization
Further, we provide theoretical and empirical analyses regarding the implications of model-usage on constrained policy optimization problems and introduce a practical algorithm that accelerates policy search with model-generated data.
Infinite Time Horizon Safety of Bayesian Neural Networks
mlech26l/bayesian_nn_safety
•
•
NeurIPS 2021
Bayesian neural networks (BNNs) place distributions over the weights of a neural network to model uncertainty in the data and the network's prediction.
