This paper proposes DeepSynth, a method for effective training of deep reinforcement
learning agents when the reward is sparse or non-Markovian, but at the same time progress …

This paper focuses on Multi-Agent Reinforcement Learning (MARL) in non-cooperative
stochastic games, particularly addressing the challenge of task completion characterized by …

Recent success in reinforcement learning (RL) has brought renewed attention to the design
of reward functions by which agent behavior is reinforced or deterred. Manually designing …

In reinforcement learning, an agent incrementally refines a behavioral policy through a
series of episodic interactions with its environment. This process can be characterized as …

Reward machines (RMs) are a recent formalism for representing the reward function of a
reinforcement learning task through a finite-state machine whose edges encode subgoals of …

The success of reinforcement learning in typical settings is predicated on Markovian
assumptions on the reward signal by which an agent learns optimal policies. In recent years …

Training reinforcement learning (RL) agents using scalar reward signals is often infeasible
when an environment has sparse and non-Markovian rewards. Moreover, handcrafting …

Solving control tasks in complex environments automatically through learning offers great
potential. While contemporary techniques from deep reinforcement learning (DRL) provide …

In this paper, we study the cooperative Multi-Agent Reinforcement Learning (MARL)
problems using Reward Machines (RMs) to specify the reward functions such that the prior …

Reinforcement learning and planning under partial observability is notoriously difficult. In
this setting, decision-making agents need to perform a sequence of actions with incomplete …