Search Results for author:
Found 23 papers, 2 papers with code
MVSA-Net: Multi-View State-Action Recognition for Robust and Deployable Trajectory Generation
Performance evaluations on two distinct domains establish that MVSA-Net recognizes the state-action pairs under occlusion more accurately compared to single-view MVSA-Net and other baselines.
A Novel Variational Lower Bound for Inverse Reinforcement Learning
In this paper, we present a new Variational Lower Bound for IRL (VLB-IRL), which is derived under the framework of a probabilistic graphical model with an optimality node.
Latent Interactive A2C for Improved RL in Open Many-Agent Systems
There is a prevalence of multiagent reinforcement learning (MARL) methods that engage in centralized training.
IRL with Partial Observations using the Principle of Uncertain Maximum Entropy
We show that in generalizing the principle of maximum entropy to these types of scenarios we unavoidably introduce a dependency on the learned model to the empirical feature expectations.
Marginal MAP Estimation for Inverse RL under Occlusion with Observer Noise
We consider the problem of learning the behavioral preferences of an expert engaged in a task from noisy and partially-observable demonstrations.
A Hierarchical Bayesian model for Inverse RL in Partially-Controlled Environments
To address this, we present a hierarchical Bayesian model that incorporates both the expert's and the confounding elements' observations thereby explicitly modeling the diverse observations a robot may receive.
Many Agent Reinforcement Learning Under Partial Observability
Recent renewed interest in multi-agent reinforcement learning (MARL) has generated an impressive array of techniques that leverage deep reinforcement learning, primarily actor-critic architectures, and can be applied to a limited range of settings in terms of observability and communication.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Cooperative-Competitive Reinforcement Learning with History-Dependent Rewards
As such, the individual agent in the organization must cooperate and compete.
Recurrent Sum-Product-Max Networks for Decision Making in Perfectly-Observed Environments
However, SPMNs are not well suited for sequential decision making over multiple time steps.
Maximum Entropy Multi-Task Inverse RL
The learner aims to learn the multiple reward functions that guide these ways of solving the problem.
Online Structure Learning for Feed-Forward and Recurrent Sum-Product Networks
Sum-product networks have recently emerged as an attractive representation due to their dual view as a special type of deep neural network with clear semantics and a special type of probabilistic graphical model for which inference is always tractable.
A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress
By categorically surveying the current literature in IRL, this article serves as a reference for researchers and practitioners of machine learning and beyond to understand the challenges of IRL and select the approaches best suited for the problem on hand.
Reinforcement Learning for Heterogeneous Teams with PALO Bounds
We introduce reinforcement learning for heterogeneous teams in which rewards for an agent are additively factored into local costs, stimuli unique to each agent, and global rewards, those shared by all agents in the domain.
A Framework and Method for Online Inverse Reinforcement Learning
Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task.
Inverse Reinforcement Learning Under Noisy Observations
Instead, a noisy continuous-time observation of the trajectory is provided to the learner.
Freeway Merging in Congested Traffic based on Multipolicy Decision Making with Passive Actor Critic
Freeway merging in congested traffic is a significant challenge toward fully automated driving.
Actor-Critic for Linearly-Solvable Continuous MDP with Partially Known Dynamics
In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model.
Individual Planning in Infinite-Horizon Multiagent Settings: Inference, Structure and Scalability
This paper provides the first formalization of self-interested planning in multiagent settings using expectation-maximization (EM).
Dynamic Sum Product Networks for Tractable Inference on Sequence Data (Extended Version)
Since SPNs represent distributions over a fixed set of variables only, we propose dynamic sum product networks (DSPNs) as a generalization of SPNs for sequence data of varying length.
Individual Planning in Agent Populations: Exploiting Anonymity and Frame-Action Hypergraphs
Traditional I-POMDPs model this dependence on the actions of other agents using joint action and model spaces.
Team Behavior in Interactive Dynamic Influence Diagrams with Applications to Ad Hoc Teams
This motivates investigating the ad hoc teamwork problem in the context of individual decision making frameworks.
Exploiting Model Equivalences for Solving Interactive Dynamic Influence Diagrams
I-DIDs are graphical models and may be used to compute the policy of an agent given its belief over the physical state and others models, which changes as the agent acts and observes in the multiagent setting.
Monte Carlo Sampling Methods for Approximating Interactive POMDPs
The interactive PF is able to mitigate the belief space complexity, but it does not address the policy space complexity.
