Search Results for author:
Found 26 papers, 3 papers with code
RL$^3$: Boosting Meta Reinforcement Learning via RL inside RL$^2$
Meta reinforcement learning (meta-RL) methods such as RL$^2$ have emerged as promising approaches for learning data-efficient RL algorithms tailored to a given task distribution.
Adaptive Rollout Length for Model-Based RL Using Model-Free Deep RL
Model-based reinforcement learning promises to learn an optimal policy from fewer interactions with the environment compared to model-free reinforcement learning by learning an intermediate model of the environment in order to predict future interactions.
Dense Crowd Flow-Informed Path Planning
In the case of pedestrian-unaware mobile robots this desire for safety leads to the freezing robot problem, where a robot confronted with a large dynamic group of obstacles (such as a crowd of pedestrians) would determine all forward navigation unsafe causing the robot to stop in place.
Causal Explanations for Sequential Decision Making Under Uncertainty
We introduce a novel framework for causal explanations of stochastic, sequential decision-making systems built on the well-studied structural causal model paradigm for causal reasoning.
Competence-Aware Path Planning via Introspective Perception
First, perception errors are learned in a model-free and location-agnostic setting via introspective perception prior to deployment in novel environments.
Agent-aware State Estimation in Autonomous Vehicles
Autonomous systems often operate in environments where the behavior of multiple agents is coordinated by a shared global state.
Mitigating Negative Side Effects via Environment Shaping
The human shapes the environment through minor reconfiguration actions so as to mitigate the impacts of the agent's side effects, without affecting the agent's ability to complete its assigned task.
Learning to Generate Fair Clusters from Demonstrations
Empirical evaluation on three real-world datasets demonstrates the effectiveness of our approach in quickly identifying the underlying fairness and interpretability constraints, which are then used to generate fair and interpretable clusters.
Helpfulness as a Key Metric of Human-Robot Collaboration
As robotic teammates become more common in society, people will assess the robots' roles in their interactions along many dimensions.
Avoiding Negative Side Effects due to Incomplete Knowledge of AI Systems
Learning to recognize and avoid such negative side effects of an agent's actions is critical to improve the safety and reliability of autonomous systems.
Improving Competence for Reliable Autonomy
Given the complexity of real-world, unstructured domains, it is often impossible or impractical to design models that include every feature needed to handle all possible scenarios that an autonomous system may encounter.
Learning to Optimize Autonomy in Competence-Aware Systems
Interest in semi-autonomous systems (SAS) is growing rapidly as a paradigm to deploy autonomous systems in domains that require occasional reliance on humans.
Balancing the Tradeoff Between Clustering Value and Interpretability
The interpretability of the clusters is complemented by generating simple explanations denoting the feature values of the nodes in the clusters, using frequent pattern mining.
Responsive Planning and Recognition for Closed-Loop Interaction
Many intelligent systems currently interact with others using at least one of fixed communication inputs or preset responses, resulting in rigid interaction experiences and extensive efforts developing a variety of scenarios for the system.
Minimizing the Negative Side Effects of Planning with Reduced Models
To that end, we propose planning using a portfolio of reduced models, a planning paradigm that minimizes the negative side effects of planning using reduced models by alternating between different outcome selection approaches.
Lexicographically Ordered Multi-Objective Clustering
We introduce a rich model for multi-objective clustering with lexicographic ordering over objectives and a slack.
Planning in Stochastic Environments with Goal Uncertainty
The framework extends the stochastic shortest path (SSP) model to dynamic environments in which it is impossible to determine the exact goal states ahead of plan execution.
An Anytime Algorithm for Task and Motion MDPs
We present a new approach where the high-level decision problem occurs in a stochastic setting and can be modeled as a Markov decision process.
Generalizing the Role of Determinization in Probabilistic Planning
The stochastic shortest path problem (SSP) is a highly expressive model for probabilistic planning.
Robust Optimization for Tree-Structured Stochastic Network Design
We therefore address the robust river network design problem where the goal is to optimize river connectivity for fish movement by removing barriers.
Stochastic Network Design in Bidirected Trees
We investigate the problem of stochastic network design in bidirected trees.
A Bilinear Programming Approach for Multiagent Planning
Because the algorithm is formulated for bilinear programs, it is more general and simpler to implement.
Policy Iteration for Decentralized Control of Markov Decision Processes
The main contribution of this paper is an optimal policy iteration algorithm for solving DEC-POMDPs.
MAP Estimation for Graphical Models by Likelihood Maximization
We experiment on the real-world protein design dataset and show that EM's convergence rate is significantly higher than the previous LP relaxation based approach MPLP.
Complexity of Decentralized Control: Special Cases
The worst-case complexity of general decentralized POMDPs, which are equivalent to partially observable stochastic games (POSGs) is very high, both for the cooperative and competitive cases.
Robust Value Function Approximation Using Bilinear Programming
Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds.
