5 papers · 1 filter
Refined Analysis of Entropy-Regularized Actor-Critic
Safwan Labbi, Paul Mangold, Daniil Tiapkin +1
In this paper, we study the role of the critic in actor--critic for entropy-regularized, finite, discounted environments. We establish that, when the critic is exact, using the lat…
Uniform Diffusion Models Revisited: Leave-One-Out Denoiser and Absorbing State Reformulation
Samson Gourevitch, Yazid Janati, Dario Shariatian +4
Discrete diffusion models are often trained through clean-data prediction, but the prediction can be used in different ways to define the reverse dynamics. In Masked Diffusion Mode…
Regret and Sample Complexity of Online Q-Learning via Concentration of Stochastic Approximation with Time-Inhomogeneous Markov Chains
Rahul Singh, Siddharth Chandak, Eric Moulines +2
We present the first regret bound for classical online Q-learning in infinite-horizon discounted Markov decision processes (MDPs), without relying on optimism or bonus terms. We fi…
Policy Gradient Methods for Non-Markovian Reinforcement Learning
Avik Kar, Siddharth Chandak, Rahul Singh +4
We study policy gradient methods for reinforcement learning in non-Markovian decision processes (NMDPs), where observations and rewards depend on the entire interaction history. To…
High-Probability Bounds for SGD under the Polyak-Lojasiewicz Condition with Markovian Noise
Avik Kar, Siddharth Chandak, Rahul Singh +3
We present the first uniform-in-time high-probability bound for SGD under the PL condition, where the gradient noise contains both Markovian and martingale difference components. T…