no code implementations • 14 Nov 2023 • Ehsan Asali, Prashant Doshi, Jin Sun
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.
no code implementations • 7 Nov 2023 • Yikang Gui, Prashant Doshi
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.
no code implementations • 9 May 2023 • Keyang He, Prashant Doshi, Bikramjit Banerjee
There is a prevalence of multiagent reinforcement learning (MARL) methods that engage in centralized training.
no code implementations • 15 Aug 2022 • Kenneth Bogert, Yikang Gui, Prashant Doshi
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.
no code implementations • 16 Sep 2021 • Prasanth Sengadu Suresh, Prashant Doshi
We consider the problem of learning the behavioral preferences of an expert engaged in a task from noisy and partially-observable demonstrations.
no code implementations • 13 Jul 2021 • Kenneth Bogert, Prashant Doshi
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.
no code implementations • 17 Jun 2021 • Keyang He, Prashant Doshi, Bikramjit Banerjee
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
no code implementations • 15 Oct 2020 • Keyang He, Bikramjit Banerjee, Prashant Doshi
As such, the individual agent in the organization must cooperate and compete.
1 code implementation • 12 Jun 2020 • Hari Teja Tatavarti, Prashant Doshi, Layton Hayes
However, SPMNs are not well suited for sequential decision making over multiple time steps.
1 code implementation • 27 Apr 2020 • Saurabh Arora, Bikramjit Banerjee, Prashant Doshi
The learner aims to learn the multiple reward functions that guide these ways of solving the problem.
no code implementations • NeurIPS 2018 • Agastya Kalra, Abdullah Rashwan, Wei-Shou Hsu, Pascal Poupart, Prashant Doshi, Georgios Trimponias
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.
no code implementations • 18 Jun 2018 • Saurabh Arora, Prashant Doshi
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.
no code implementations • 23 May 2018 • Roi Ceren, Prashant Doshi, Keyang He
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.
no code implementations • 21 May 2018 • Saurabh Arora, Prashant Doshi, Bikramjit Banerjee
Inverse reinforcement learning (IRL) is the problem of learning the preferences of an agent from the observations of its behavior on a task.
no code implementations • 27 Oct 2017 • Shervin Shahryari, Prashant Doshi
Instead, a noisy continuous-time observation of the trajectory is provided to the learner.
no code implementations • 14 Jul 2017 • Tomoki Nishi, Prashant Doshi, Danil Prokhorov
Freeway merging in congested traffic is a significant challenge toward fully automated driving.
no code implementations • 4 Jun 2017 • Tomoki Nishi, Prashant Doshi, Michael R. James, Danil Prokhorov
In many robotic applications, some aspects of the system dynamics can be modeled accurately while others are difficult to obtain or model.
no code implementations • NeurIPS 2015 • Xia Qu, Prashant Doshi
This paper provides the first formalization of self-interested planning in multiagent settings using expectation-maximization (EM).
no code implementations • 13 Nov 2015 • Mazen Melibari, Pascal Poupart, Prashant Doshi, George Trimponias
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.
no code implementations • 24 Mar 2015 • Ekhlas Sonu, Yingke Chen, Prashant Doshi
Traditional I-POMDPs model this dependence on the actions of other agents using joint action and model spaces.
no code implementations • 1 Sep 2014 • Muthukumaran Chandrasekaran, Prashant Doshi, Yifeng Zeng, Yingke Chen
This motivates investigating the ad hoc teamwork problem in the context of individual decision making frameworks.
no code implementations • 18 Jan 2014 • Yifeng Zeng, Prashant Doshi
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.
no code implementations • 15 Jan 2014 • Prashant Doshi, Piotr J. Gmytrasiewicz
The interactive PF is able to mitigate the belief space complexity, but it does not address the policy space complexity.