7 papers
An Agency-Transferring Model-Free Policy Enhancement Technique
Anton Bolychev, Georgiy Malaniya, Sinan Ibrahim +1
Training reinforcement learning (RL) policies from scratch is costly: it requires careful reward and environment design, extensive tuning, and substantial computation. Yet many con…
A universal policy wrapper with guarantees
Anton Bolychev, Georgiy Malaniya, Grigory Yaremenko +2
We introduce a universal policy wrapper for reinforcement learning agents that ensures formal goal-reaching guarantees. In contrast to standard reinforcement learning algorithms th…
Multi-CALF: A Policy Combination Approach with Statistical Guarantees
Georgiy Malaniya, Anton Bolychev, Grigory Yaremenko +2
We introduce Multi-CALF, an algorithm that intelligently combines reinforcement learning policies based on their relative value improvements. Our approach integrates a standard RL…
An agent design with goal reaching guarantees for enhancement of learning
Pavel Osinenko, Grigory Yaremenko, Georgiy Malaniya +2
Reinforcement learning is commonly concerned with problems of maximizing accumulated rewards in Markov decision processes. Oftentimes, a certain goal state or a subset of the state…
A framework for online, stabilizing reinforcement learning
Grigory Yaremenko, Georgiy Malaniya, Pavel Osinenko
Online reinforcement learning is concerned with training an agent on-the-fly via dynamic interaction with the environment. Here, due to the specifics of the application, it is not…
On stochastic stabilization via non-smooth control Lyapunov functions
Pavel Osinenko, Grigory Yaremenko, Georgiy Malaniya
Control Lyapunov function is a central tool in stabilization. It generalizes an abstract energy function -- a Lyapunov function -- to the case of controlled systems. It is a known…
A generalized stacked reinforcement learning method for sampled systems
Pavel Osinenko, Dmitrii Dobriborsci, Grigory Yaremenko +1
A common setting of reinforcement learning (RL) is a Markov decision process (MDP) in which the environment is a stochastic discrete-time dynamical system. Whereas MDPs are suitabl…