In recent decades, Reinforcement Learning (RL) has emerged as an effective approach to address complex control tasks. In a Markov Decision Process (MDP), the framework typically …
In many real-world problems, there is the possibility to configure, to a limited extent, some environmental parameters to improve the performance of a learning agent. In this paper, we …
Abstract Configurable Markov Decision Processes (Conf-MDPs) have been recently introduced as an extension of the usual MDP model to account for the possibility of …
Y Liu, A Halev, X Liu - The 30th international joint conference on artificial …, 2021 - par.nsf.gov
Reinforcement Learning (RL) algorithms have had tremendous success in simulated domains. These algorithms, however, often cannot be directly applied to physical systems …
G Ramponi, AM Metelli, A Concetti… - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract The Configurable Markov Decision Process framework includes two entities: a Reinforcement Learning agent and a configurator that can modify some environmental …
One of the central challenges faced by a reinforcement learning (RL) agent is to effectively learn a (near-) optimal policy in environments with large state spaces having sparse and …
In Reinforcement Learning (RL) the goal is to find a policy π that maximizes the expected future return, calculated based on a scalar reward function R (·)∈ R. The policy π …
We study the problem of identifying the policy space available to an agent in a learning process, having access to a set of demonstrations generated by the agent playing the …
Producing agents that can generalize to a wide range of environments is a significant challenge in reinforcement learning. One method for overcoming this issue is domain …