Exploring Pessimism and Optimism Dynamics in Deep Reinforcement Learning

no code implementations • 6 Jun 2024 • Bahareh Tasdighi, Nicklas Werge, Yi-Shan Wu, Melih Kandemir

Based on these insights, we introduce Utility Soft Actor-Critic (USAC), a novel framework within the actor-critic paradigm that enables independent control over the degree of pessimism/optimism for both the actor and the critic via interpretable parameters.

Continuous Control reinforcement-learning

Probabilistic Actor-Critic: Learning to Explore with PAC-Bayes Uncertainty

no code implementations • 5 Feb 2024 • Bahareh Tasdighi, Nicklas Werge, Yi-Shan Wu, Melih Kandemir

We introduce Probabilistic Actor-Critic (PAC), a novel reinforcement learning algorithm with improved continuous control performance thanks to its ability to mitigate the exploration-exploitation trade-off.

Continuous Control Decision Making +1

PAC-Bayesian Soft Actor-Critic Learning

no code implementations • 30 Jan 2023 • Bahareh Tasdighi, Abdullah Akgül, Kenny Kazimirzak Brink, Melih Kandemir

Actor-critic algorithms address the dual goals of reinforcement learning (RL), policy evaluation and improvement, via two separate function approximators.

Reinforcement Learning (RL)