Raghuram Bharadwaj Diddigi

Ritish Shrirao, Aditya Priyadarshi, Raghuram Bharadwaj Diddigi

Successor Features (SF) combined with Generalized Policy Improvement (GPI) provide a robust framework for transfer learning in Reinforcement Learning (RL) by decoupling environment dynamics from reward functions. However, standard SF learning methods typically rely on semi-gradient Temporal Difference (TD) updates. When combined with non-linear function approximation, semi-gradient methods lack robust convergence guarantees and can lead to instability, particularly in the multi-task setting where accurate feature estimation is critical for effective GPI. Inspired by Full Gradient DQN, we propose Full-Gradient Successor Feature Representations Q-Learning (FG-SFRQL), an algorithm that optimizes the successor features by minimizing the full Mean Squared Bellman Error. Unlike standard approaches, our method computes gradients with respect to parameters in both the online and target networks. We provide a theoretical proof of almost-sure convergence for FG-SFRQL and demonstrate empirically that minimizing the full residual leads to superior sample efficiency and transfer performance compared to semi-gradient baselines in both discrete and continuous domains.

Chainesh Gautam, Raghuram Bharadwaj Diddigi

Recently, there has been an increasing need to develop agents capable of solving multiple tasks within the same environment, especially when these tasks are naturally associated with language. In this work, we propose a novel approach that leverages combinations of pre-trained (language, policy) pairs to establish an efficient transfer pipeline. Our algorithm is inspired by the principles of Contrastive Language-Image Pretraining (CLIP) in Computer Vision, which aligns representations across different modalities under the philosophy that ''two modalities representing the same concept should have similar representations.'' The central idea here is that the instruction and corresponding policy of a task represent the same concept, the task itself, in two different modalities. Therefore, by extending the idea of CLIP to RL, our method creates a unified representation space for natural language and policy embeddings. Experimental results demonstrate the utility of our algorithm in achieving faster transfer across tasks.

Kausthubh Manda, Raghuram Bharadwaj Diddigi

We study offline multitask reinforcement learning in settings where multiple tasks share a low-rank representation of their action-value functions. In this regime, a learner is provided with fixed datasets collected from several related tasks, without access to further online interaction, and seeks to exploit shared structure to improve statistical efficiency and generalization. We analyze a multitask variant of fitted Q-iteration that jointly learns a shared representation and task-specific value functions via Bellman error minimization on offline data. Under standard realizability and coverage assumptions commonly used in offline reinforcement learning, we establish finite-sample generalization guarantees for the learned value functions. Our analysis explicitly characterizes how pooling data across tasks improves estimation accuracy, yielding a $1/\sqrt{nT}$ dependence on the total number of samples across tasks, while retaining the usual dependence on the horizon and concentrability coefficients arising from distribution shift. In addition, we consider a downstream offline setting in which a new task shares the same underlying representation as the upstream tasks. We study how reusing the representation learned during the multitask phase affects value estimation for this new task, and show that it can reduce the effective complexity of downstream learning relative to learning from scratch. Together, our results clarify the role of shared representations in multitask offline Q-learning and provide theoretical insight into when and how multitask structure can improve generalization in model-free, value-based reinforcement learning.

Sooraj Sathish, Keshav Goyal, Raghuram Bharadwaj Diddigi

Deep Reinforcement Learning (RL) has demonstrated success in solving complex sequential decision-making problems by integrating neural networks with the RL framework. However, training deep RL models poses several challenges, such as the need for extensive hyperparameter tuning and high computational costs. Transfer learning has emerged as a promising strategy to address these challenges by enabling the reuse of knowledge from previously learned tasks for new, related tasks. This avoids the need for retraining models entirely from scratch. A commonly used approach for transfer learning in RL is to leverage the internal representations learned by the neural network during training. Specifically, the activations from the last hidden layer can be viewed as refined state representations that encapsulate the essential features of the input. In this work, we investigate whether these representations can be used as input for training simpler models, such as linear function approximators, on new tasks. We observe that the representations learned by standard deep RL models can be highly correlated, which limits their effectiveness when used with linear function approximation. To mitigate this problem, we propose a novel deep Q-learning approach that introduces a regularization term to reduce positive correlations between feature representation of states. By leveraging these reduced correlated features, we enable more effective use of linear function approximation in transfer learning. Through experiments and ablation studies on standard RL benchmarks and MinAtar games, we demonstrate the efficacy of our approach in improving transfer learning performance and thereby reducing computational overhead.

Nandakishore S Menon, Chandramouli Kamanchi, Raghuram Bharadwaj Diddigi

Our work aims to build a model that performs dual tasks of image captioning and image generation while being trained on only one task. The central idea is to train an invertible model that learns a one-to-one mapping between the image and text embeddings. Once the invertible model is efficiently trained on one task, the image captioning, the same model can generate new images for a given text through the inversion process, with no additional training. This paper proposes a simple invertible neural network architecture for this problem and presents our current findings.

Raghuram Bharadwaj Diddigi, Prateek Jain, Prabuchandran K. J. et al.

Learning optimal behavior from existing data is one of the most important problems in Reinforcement Learning (RL). This is known as "off-policy control" in RL where an agent's objective is to compute an optimal policy based on the data obtained from the given policy (known as the behavior policy). As the optimal policy can be very different from the behavior policy, learning optimal behavior is very hard in the "off-policy" setting compared to the "on-policy" setting where new data from the policy updates will be utilized in learning. This work proposes an off-policy natural actor-critic algorithm that utilizes state-action distribution correction for handling the off-policy behavior and the natural policy gradient for sample efficiency. The existing natural gradient-based actor-critic algorithms with convergence guarantees require fixed features for approximating both policy and value functions. This often leads to sub-optimal learning in many RL applications. On the other hand, our proposed algorithm utilizes compatible features that enable one to use arbitrary neural networks to approximate the policy and the value function and guarantee convergence to a locally optimal policy. We illustrate the benefit of the proposed off-policy natural gradient algorithm by comparing it with the vanilla gradient actor-critic algorithm on benchmark RL tasks.

P. Parnika, Raghuram Bharadwaj Diddigi, Sai Koti Reddy Danda et al.

In this work, we consider the problem of computing optimal actions for Reinforcement Learning (RL) agents in a co-operative setting, where the objective is to optimize a common goal. However, in many real-life applications, in addition to optimizing the goal, the agents are required to satisfy certain constraints specified on their actions. Under this setting, the objective of the agents is to not only learn the actions that optimize the common objective but also meet the specified constraints. In recent times, the Actor-Critic algorithm with an attention mechanism has been successfully applied to obtain optimal actions for RL agents in multi-agent environments. In this work, we extend this algorithm to the constrained multi-agent RL setting. The idea here is that optimizing the common goal and satisfying the constraints may require different modes of attention. By incorporating different attention modes, the agents can select useful information required for optimizing the objective and satisfying the constraints separately, thereby yielding better actions. Through experiments on benchmark multi-agent environments, we show the effectiveness of our proposed algorithm.

Raghuram Bharadwaj Diddigi, Chandramouli Kamanchi, Shalabh Bhatnagar

Learning the value function of a given policy (target policy) from the data samples obtained from a different policy (behavior policy) is an important problem in Reinforcement Learning (RL). This problem is studied under the setting of off-policy prediction. Temporal Difference (TD) learning algorithms are a popular class of algorithms for solving the prediction problem. TD algorithms with linear function approximation are shown to be convergent when the samples are generated from the target policy (known as on-policy prediction). However, it has been well established in the literature that off-policy TD algorithms under linear function approximation diverge. In this work, we propose a convergent on-line off-policy TD algorithm under linear function approximation. The main idea is to penalize the updates of the algorithm in a way as to ensure convergence of the iterates. We provide a convergence analysis of our algorithm. Through numerical evaluations, we further demonstrate the effectiveness of our algorithm.

Raghuram Bharadwaj Diddigi, Chandramouli Kamanchi, Shalabh Bhatnagar

We consider the problem of two-player zero-sum games. This problem is formulated as a min-max Markov game in the literature. The solution of this game, which is the min-max payoff, starting from a given state is called the min-max value of the state. In this work, we compute the solution of the two-player zero-sum game utilizing the technique of successive relaxation that has been successfully applied in the literature to compute a faster value iteration algorithm in the context of Markov Decision Processes. We extend the concept of successive relaxation to the setting of two-player zero-sum games. We show that, under a special structure on the game, this technique facilitates faster computation of the min-max value of the states. We then derive a generalized minimax Q-learning algorithm that computes the optimal policy when the model information is not known. Finally, we prove the convergence of the proposed generalized minimax Q-learning algorithm utilizing stochastic approximation techniques, under an assumption on the boundedness of iterates. Through experiments, we demonstrate the effectiveness of our proposed algorithm.

Chandramouli Kamanchi, Raghuram Bharadwaj Diddigi, Shalabh Bhatnagar

Value iteration is a fixed point iteration technique utilized to obtain the optimal value function and policy in a discounted reward Markov Decision Process (MDP). Here, a contraction operator is constructed and applied repeatedly to arrive at the optimal solution. Value iteration is a first order method and therefore it may take a large number of iterations to converge to the optimal solution. Successive relaxation is a popular technique that can be applied to solve a fixed point equation. It has been shown in the literature that, under a special structure of the MDP, successive over-relaxation technique computes the optimal value function faster than standard value iteration. In this work, we propose a second order value iteration procedure that is obtained by applying the Newton-Raphson method to the successive relaxation value iteration scheme. We prove the global convergence of our algorithm to the optimal solution asymptotically and show the second order convergence. Through experiments, we demonstrate the effectiveness of our proposed approach.

Chandramouli Kamanchi, Raghuram Bharadwaj Diddigi, Shalabh Bhatnagar

In a discounted reward Markov Decision Process (MDP), the objective is to find the optimal value function, i.e., the value function corresponding to an optimal policy. This problem reduces to solving a functional equation known as the Bellman equation and a fixed point iteration scheme known as the value iteration is utilized to obtain the solution. In literature, a successive over-relaxation based value iteration scheme is proposed to speed-up the computation of the optimal value function. The speed-up is achieved by constructing a modified Bellman equation that ensures faster convergence to the optimal value function. However, in many practical applications, the model information is not known and we resort to Reinforcement Learning (RL) algorithms to obtain optimal policy and value function. One such popular algorithm is Q-learning. In this paper, we propose Successive Over-Relaxation (SOR) Q-learning. We first derive a modified fixed point iteration for SOR Q-values and utilize stochastic approximation to derive a learning algorithm to compute the optimal value function and an optimal policy. We then prove the almost sure convergence of the SOR Q-learning to SOR Q-values. Finally, through numerical experiments, we show that SOR Q-learning is faster compared to the standard Q-learning algorithm.

Chandramouli Kamanchi, Raghuram Bharadwaj Diddigi, Prabuchandran K. J. et al.

One of the popular measures of central tendency that provides better representation and interesting insights of the data compared to the other measures like mean and median is the metric mode. If the analytical form of the density function is known, mode is an argument of the maximum value of the density function and one can apply the optimization techniques to find mode. In many of the practical applications, the analytical form of the density is not known and only the samples from the distribution are available. Most of the techniques proposed in the literature for estimating the mode from the samples assume that all the samples are available beforehand. Moreover, some of the techniques employ computationally expensive operations like sorting. In this work we provide a computationally effective, on-line iterative algorithm that estimates the mode of a unimodal smooth density given only the samples generated from the density. Asymptotic convergence of the proposed algorithm using an ordinary differential equation (ODE) based analysis is provided. We also prove the stability of estimates by utilizing the concept of regularization. Experimental results further demonstrate the effectiveness of the proposed algorithm.

Raghuram Bharadwaj Diddigi, Prabuchandran K. J., Shalabh Bhatnagar

We consider the problem of tracking an intruder using a network of wireless sensors. For tracking the intruder at each instant, the optimal number and the right configuration of sensors has to be powered. As powering the sensors consumes energy, there is a trade off between accurately tracking the position of the intruder at each instant and the energy consumption of sensors. This problem has been formulated in the framework of Partially Observable Markov Decision Process (POMDP). Even for the state-of-the-art algorithm in the literature, the curse of dimensionality renders the problem intractable. In this paper, we formulate the Intrusion Detection (ID) problem with a suitable state-action space in the framework of POMDP and develop a Reinforcement Learning (RL) algorithm utilizing the Upper Confidence Tree Search (UCT) method to solve the ID problem. Through simulations, we show that our algorithm performs and scales well with the increasing state and action spaces.

Raghuram Bharadwaj Diddigi, D. Sai Koti Reddy, Shalabh Bhatnagar

We consider the problem of minimizing the difference in the demand and the supply of power using microgrids. We setup multiple microgrids, that provide electricity to a village. They have access to the batteries that can store renewable power and also the electrical lines from the main grid. During each time period, these microgrids need to take decision on the amount of renewable power to be used from the batteries as well as the amount of power needed from the main grid. We formulate this problem in the framework of Markov Decision Process (MDP), similar to the one discussed in [1]. The power allotment to the village from the main grid is fixed and bounded, whereas the renewable energy generation is uncertain in nature. Therefore we adapt a distributed version of the popular Reinforcement learning technique, Multi-Agent Q-Learning to the problem. Finally, we also consider a variant of this problem where the cost of power production at the main site is taken into consideration. In this scenario the microgrids need to minimize the demand-supply deficit, while maintaining the desired average cost of the power production.