This work presents a new class of algorithms named Continuous Actor Critic Learning Automaton (CACLA) that can handle continuous states and actions that is straightforward to implement and an experimental comparison is made between this algorithm and other algorithms that can handle continuous action spaces.
This work proposes Continuous Nested Monte Carlo Search and Continuous Nested Rollout Policy Adaptation and shows that they provide promising results on three problems: Map Traveling, Mountain Car Continuous and two instances of Chemical Processes from the pc-gym package.
This work states that there has been an upsurge of interest and development of RL theory and applications in the communities of stochastic control, stochastic analysis and unsupervised learning.
Xin Guo, Xun-Yu Zhou· Applied Mathematics and Opti...· 0 citations
This dissertation presents a work in safe RL, where agents must also respect safety constraints using pure-past linear-time temporal logic (PPLTL), and presents how to enforce safety constraints using pure-past linear-time temporal logic (PPLTL).
Reinforcement learning in real-life applications requires safety guarantees during exploration. Typical reinforcement learning algorithms do not provide such guarantees, and many modifications that do rely on Gaussian processes (GPs), which have a large computational cost. We propose a computationally lightweight algor...
Shreeram Murali, Shankar A. Deka, Dominik Baumann· 0 citations
This paper explores the potential-theoretic viewpoint for core reinforcement learning representations and algorithms under a fixed-policy assumption and may offer a path for improved sample efficiency and formal constraints that can be applied to RL.
This work explores using diffusion models as a representation for the state successor measure and finds that enforcing the Bellman flow constraints on a diffusion model leads to a temporal difference update on the predicted noise, similar to the standard TD-learning update on the predicted reward.
Liam Schramm, Abdeslam Boularias· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
