Search Results for author:
Found 15 papers, 0 papers with code
On the Global Convergence of Fitted Q-Iteration with Two-layer Neural Network Parametrization
Deep Q-learning based algorithms have been applied successfully in many decision making problems, while their theoretical foundations are not as well understood.
Achieving Zero Constraint Violation for Constrained Reinforcement Learning via Primal-Dual Approach
To achieve that, we advocate the use of randomized primal-dual approach to solve the CMDP problems and propose a conservative stochastic primal-dual algorithm (CSPDA) which is shown to exhibit $\tilde{\mathcal{O}}\left(1/\epsilon^2\right)$ sample complexity to achieve $\epsilon$-optimal cumulative reward with zero constraint violations.
Concave Utility Reinforcement Learning with Zero-Constraint Violations
We consider the problem of tabular infinite horizon concave utility reinforcement learning (CURL) with convex constraints.
On the Approximation of Cooperative Heterogeneous Multi-Agent Reinforcement Learning (MARL) using Mean Field Control (MFC)
We show that, in these cases, the $K$-class MARL problem can be approximated by MFC with errors given as $e_1=\mathcal{O}(\frac{\sqrt{|\mathcal{X}|}+\sqrt{|\mathcal{U}|}}{N_{\mathrm{pop}}}\sum_{k}\sqrt{N_k})$, $e_2=\mathcal{O}(\left[\sqrt{|\mathcal{X}|}+\sqrt{|\mathcal{U}|}\right]\sum_{k}\frac{1}{\sqrt{N_k}})$ and $e_3=\mathcal{O}\left(\left[\sqrt{|\mathcal{X}|}+\sqrt{|\mathcal{U}|}\right]\left[\frac{A}{N_{\mathrm{pop}}}\sum_{k\in[K]}\sqrt{N_k}+\frac{B}{\sqrt{N_{\mathrm{pop}}}}\right]\right)$, respectively, where $A, B$ are some constants and $|\mathcal{X}|,|\mathcal{U}|$ are the sizes of state and action spaces of each agent.
Markov Decision Processes with Long-Term Average Constraints
We consider the problem of constrained Markov Decision Process (CMDP) where an agent interacts with a unichain Markov Decision Process.
Joint Optimization of Multi-Objective Reinforcement Learning with Policy Gradient Based Algorithm
Many engineering problems have multiple objectives, and the overall aim is to optimize a non-linear function of these objectives.
Multi-Objective Reinforcement Learning
reinforcement-learning
Communication Efficient Parallel Reinforcement Learning
We provide \NAM\ which runs at each agent and prove that the total cumulative regret of $M$ agents is upper bounded as $\Tilde{O}(DS\sqrt{MAT})$ for a Markov Decision Process with diameter $D$, number of states $S$, and number of actions $A$.
Multi-Agent Multi-Armed Bandits with Limited Communication
With our algorithm, LCC-UCB, each agent enjoys a regret of $\tilde{O}\left(\sqrt{({K/N}+ N)T}\right)$, communicates for $O(\log T)$ steps and broadcasts $O(\log K)$ bits in each communication step.
Blind Decision Making: Reinforcement Learning with Delayed Observations
This paper proposes an approach, where the delay in the knowledge of the state can be used, and the decisions are made based on the available information which may not include the current state information.
DART: aDaptive Accept RejecT for non-linear top-K subset identification
Additionally, our algorithm works on correlated rewards of individual arms.
Escaping Saddle Points for Zeroth-order Nonconvex Optimization using Estimated Gradient Descent
Gradient descent and its variants are widely used in machine learning.
Encoders and Decoders for Quantum Expander Codes Using Machine Learning
However, large-scale design of quantum encoders and decoders have to depend on the channel characteristics and require look-up tables which require memory that is exponential in the number of qubits.
Reinforcement Learning for Joint Optimization of Multiple Rewards
Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation.
Reinforcement Learning for Mean Field Game
This paper focuses on finding a mean-field equilibrium (MFE) in an action coupled stochastic game setting in an episodic framework.
Stochastic Top-$K$ Subset Bandits with Linear Space and Non-Linear Feedback
Many real-world problems like Social Influence Maximization face the dilemma of choosing the best $K$ out of $N$ options at a given time instant.
