Jhelum Chakravorty

Jhelum Chakravorty, Aditya Mahajan

We investigate a remote estimation problem in which a transmitter observes a Markov source and chooses the power level to transmit it over a time-varying packet-drop channel. The channel is modeled as a channel with Markovian state where the packet drop probability depends on the channel state and the transmit power. A receiver observes the channel output and the channel state and estimates the source realization. The receiver also feeds back the channel state and an acknowledgment for successful reception to the transmitter. We consider two models for the source---finite state Markov chains and first-order autoregressive processes. For the first model, using ideas from team theory, we establish the structure of optimal transmission and estimation strategies and identify a dynamic program to determine optimal strategies with that structure. For the second model, we assume that the noise process has unimodal and symmetric distribution. Using ideas from majorization theory, we show that the optimal transmission strategy is symmetric and monotonic and the optimal estimation strategy is like Kalman filter. Consequently, when there are a finite number of power levels, the optimal transmission strategy may be described using thresholds that depend on the channel state. Finally, we propose a simulation based approach (Renewal Monte Carlo) to compute the optimal thresholds and optimal performance and elucidate the algorithm with an example.

Jhelum Chakravorty, Aditya Mahajan

The fundamental limits of remote estimation of Markov processes under communication constraints are presented. The remote estimation system consists of a sensor and an estimator. The sensor observes a discrete-time Markov process, which is a symmetric countable state Markov source or a Gauss-Markov process. At each time, the sensor either transmits the current state of the Markov process or does not transmit at all. Communication is noiseless but costly. The estimator estimates the Markov process based on the transmitted observations. In such a system, there is a trade-off between communication cost and estimation accuracy. Two fundamental limits of this trade-off are characterized for infinite horizon discounted cost and average cost setups. First, when each transmission is costly, we characterize the minimum achievable cost of communication plus estimation error. Second, when there is a constraint on the average number of transmissions, we characterize the minimum achievable estimation error. Transmission and estimation strategies that achieve these fundamental limits are also identified.

David Venuto, Jhelum Chakravorty, Leonard Boussioux et al.

Explicit engineering of reward functions for given environments has been a major hindrance to reinforcement learning methods. While Inverse Reinforcement Learning (IRL) is a solution to recover reward functions from demonstrations only, these learned rewards are generally heavily \textit{entangled} with the dynamics of the environment and therefore not portable or \emph{robust} to changing environments. Modern adversarial methods have yielded some success in reducing reward entanglement in the IRL setting. In this work, we leverage one such method, Adversarial Inverse Reinforcement Learning (AIRL), to propose an algorithm that learns hierarchical disentangled rewards with a policy over options. We show that this method has the ability to learn \emph{generalizable} policies and reward functions in complex transfer learning tasks, while yielding results in continuous control benchmarks that are comparable to those of the state-of-the-art methods.

Jhelum Chakravorty, Nadeem Ward, Julien Roy et al.

In this paper, we investigate learning temporal abstractions in cooperative multi-agent systems, using the options framework (Sutton et al, 1999). First, we address the planning problem for the decentralized POMDP represented by the multi-agent system, by introducing a \emph{common information approach}. We use the notion of \emph{common beliefs} and broadcasting to solve an equivalent centralized POMDP problem. Then, we propose the Distributed Option Critic (DOC) algorithm, which uses centralized option evaluation and decentralized intra-option improvement. We theoretically analyze the asymptotic convergence of DOC and build a new multi-agent environment to demonstrate its validity. Our experiments empirically show that DOC performs competitively against baselines and scales with the number of agents.

David Venuto, Leonard Boussioux, Junhao Wang et al.

Imitation learning seeks to learn an expert policy from sampled demonstrations. However, in the real world, it is often difficult to find a perfect expert and avoiding dangerous behaviors becomes relevant for safety reasons. We present the idea of \textit{learning to avoid}, an objective opposite to imitation learning in some sense, where an agent learns to avoid a demonstrator policy given an environment. We define avoidance learning as the process of optimizing the agent's reward while avoiding dangerous behaviors given by a demonstrator. In this work we develop a framework of avoidance learning by defining a suitable objective function for these problems which involves the \emph{distance} of state occupancy distributions of the expert and demonstrator policies. We use density estimates for state occupancy measures and use the aforementioned distance as the reward bonus for avoiding the demonstrator. We validate our theory with experiments using a wide range of partially observable environments. Experimental results show that we are able to improve sample efficiency during training compared to state of the art policy optimization and safety methods.