Search Results for author:
Found 6 papers, 0 papers with code
Deep Reinforcement Learning: A Convex Optimization Approach
That is, when the number of episodes goes to infinity, there exists a constant $C$ such that \[\|w-w^\star\| \le C\cdot\frac{\rho}{T}.\] In particular, our algorithm converges arbitrarily close to the optimal neural network parameters as the time horizon increases or as the regularization parameter decreases.
Decentralized Online Bandit Optimization on Directed Graphs with Regret Bounds
We consider a decentralized multiplayer game, played over $T$ rounds, with a leader-follower hierarchy described by a directed acyclic graph.
Model-Free Algorithm and Regret Analysis for MDPs with Long-Term Constraints
This paper uses concepts from constrained optimization and Q-learning to propose an algorithm for CMDP with long-term constraints.
Provably Efficient Model-Free Algorithm for MDPs with Peak Constraints
The proposed algorithm is proved to achieve an $(\epsilon, p)$-PAC policy when the episode $K\geq\Omega(\frac{I^2H^6SA\ell}{\epsilon^2})$, where $S$ and $A$ are the number of states and actions, respectively.
Conditional Mutual information-based Contrastive Loss for Financial Time Series Forecasting
One challenge of using deep learning models for finance forecasting is the shortage of available training data when using small datasets.
Reinforcement Learning of Markov Decision Processes with Peak Constraints
We introduce a game theoretic approach to construct reinforcement learning algorithms where the agent maximizes an unconstrained objective that depends on the simulated action of the minimizing opponent which acts on a finite set of actions and the output data of the constraint functions (rewards).
