Search Results for author:
Found 19 papers, 2 papers with code
Adaptive Primal-Dual Method for Safe Reinforcement Learning
In this paper, we propose, analyze and evaluate adaptive primal-dual (APD) methods for SRL, where two adaptive LRs are adjusted to the Lagrangian multipliers so as to optimize the policy in each iteration.
Learning Non-myopic Power Allocation in Constrained Scenarios
The problem of optimal power allocation -- for maximizing a given network utility metric -- under instantaneous constraints has recently gained significant popularity.
Blackout Mitigation via Physics-guided RL
This paper considers the sequential design of remedial control actions in response to system anomalies for the ultimate objective of preventing blackouts.
Probabilistic Constraint for Safety-Critical Reinforcement Learning
Furthermore, we propose a Safe Primal-Dual algorithm that can leverage both SPGs to learn safe policies.
Policy Gradients for Probabilistic Constrained Reinforcement Learning
In particular, we consider the notion of probabilistic safety.
Tensor and Matrix Low-Rank Value-Function Approximation in Reinforcement Learning
Value-function (VF) approximation is a central problem in Reinforcement Learning (RL).
Constrained Learning with Non-Convex Losses
In this paper, we overcome this issue by learning in the empirical dual domain, where constrained statistical learning problems become unconstrained and deterministic.
Towards Safe Continuing Task Reinforcement Learning
However, to transfer from learning safety to learning safely, there are two hurdles that need to be overcome: (i) it has to be possible to learn the policy without having to re-initialize the system; and (ii) the rollouts of the system need to be in themselves safe.
State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards
Thus, as we illustrate by an example, while previous methods can fail at finding optimal policies, running the dual dynamics while executing the augmented policy yields an algorithm that provably samples actions from the optimal policy.
Sufficiently Accurate Model Learning for Planning
This paper introduces the constrained Sufficiently Accurate model learning approach, provides examples of such problems, and presents a theorem on how close some approximate solutions can be.
Trust but Verify: Assigning Prediction Credibility by Counterfactual Constrained Learning
Prediction credibility measures, in the form of confidence intervals or probability distributions, are fundamental in statistics and machine learning to characterize model robustness, detect out-of-distribution samples (outliers), and protect against adversarial attacks.
Policy Gradient for Continuing Tasks in Non-stationary Markov Decision Processes
To that end we compute unbiased stochastic gradients of the value function which we use as ascent directions to update the policy.
Counterfactual Programming for Optimal Control
In recent years, considerable work has been done to tackle the issue of designing control laws based on observations to allow unknown dynamical systems to perform pre-specified tasks.
The empirical duality gap of constrained statistical learning
This paper is concerned with the study of constrained statistical learning problems, the unconstrained version of which are at the core of virtually all of modern information processing.
Safe Policies for Reinforcement Learning via Primal-Dual Methods
The advantages of the proposed relaxation are threefold.
Constrained Reinforcement Learning Has Zero Duality Gap
The later is generally addressed by formulating the conflicting requirements as a constrained RL problem and solved using Primal-Dual methods.
Sparse multiresolution representations with adaptive kernels
To address the complexity issues, we then write the function estimation problem as a sparse functional program that explicitly minimizes the support of the representation leading to low complexity solutions.
Sufficiently Accurate Model Learning
In this paper, we investigate a method to regularize model learning techniques to provide better error characteristics for traditional control and planning algorithms.
Decentralized Online Learning with Kernels
That is, we establish that with constant step-size selections agents' functions converge to a neighborhood of the globally optimal one while satisfying the consensus constraints as the penalty parameter is increased.
