The use of Potential-Based Reward Shaping (PBRS) has shown great promise in the ongoing research effort to tackle sample inefficiency in Reinforcement Learning (RL). However, choosing the right potential function remains an open challenge. Additionally, RL techniques are usually constrained to use a finite horizon for computational limitations, which introduces a bias when using PBRS. In this paper, we first build some theoretically-grounded intuition on why selecting the potential function as the optimal value function of the task at hand produces performance advantages. We then analyse the bias induced by finite horizons in the context of PBRS producing novel insights. Finally, leveraging abstractions as a way to approximate the optimal value function of the given task, we assess the sample efficiency and performance impact of PBRS on four environments including a goal-oriented navigation task and three Arcade Learning Environments (ALE) games. Remarkably, experimental results show that we can reach the same level of performance as CNN-based solutions with a simple fully-connected network.

We study policy optimization in Stackelberg mean field games (MFGs), a hierarchical framework for modeling the strategic interaction between a single leader and an infinitely large population of homogeneous followers. The objective can be formulated as a structured bi-level optimization problem, in which the leader needs to learn a policy maximizing its reward, anticipating the response of the followers. Existing methods for solving these (and related) problems often rely on restrictive independence assumptions between the leader’s and followers’ objectives, use samples inefficiently due to nested-loop algorithm structure, and lack finite-time convergence guarantees. To address these limitations, we propose AC-SMFG, a single-loop actor-critic algorithm that operates on continuously generated Markovian samples. The algorithm alternates between (semi-)gradient updates for the leader, a representative follower, and the mean field, and is simple to implement in practice. We establish the finite-time and finite-sample convergence of the algorithm to a stationary point of the Stackelberg objective. To our knowledge, this is the first Stackelberg MFG algorithm with non-asymptotic convergence guarantees. Our key assumption is a "gradient alignment" condition, which requires that the full policy gradient of the leader can be approximated by a partial component of it, relaxing the existing leader-follower independence assumption. Simulation results in a range of well-established economics environments demonstrate that AC-SMFG outperforms existing multi-agent and MFG learning baselines in policy quality and convergence speed.

Teams of embodied AI-enabled agents are critical for applications in extreme and highly dynamic environments. Developing robust controllers for such agents requires a deep understanding of the challenges encountered when attempting to coordinate and synchronize their individual perception-cognition-communication-action (PCCA) loops for team-wide mission objectives. We introduce a framework to explore the coordination of the PCCA loops across multiple agents in a new simulated physical environment designed to explore collaboration in each PCCA stage. This environment tasks teams of agents with the correct disposal of dangerous objects in an area and forces careful coordination of sensing, communication, movement, and manipulation actions by providing spatially-bounded communication, incorporating situations that require concerted effort by groups of agents, and introducing uncertainty into agents’ sensing capabilities. We provide a set of heuristic controllers, an offline oracle model, and an initial exploration of a Reward Machine-based controller that learns its policies from training. Together these approaches serve to provide insights into the complexity of the multi-agent PCCA loop coordination problem. The multiagent PCCA simulation environment, which supports AI and human-controlled agents, and the code for various agent controllers are available at https://github.com/nesl/AI-Collab.

This paper presents PROB-IRM, an approach that learns robust reward machines (RMs) for reinforcement learning (RL) agents from noisy execution traces. The key aspect of RM-driven RL is the exploitation of a finite-state ma- chine that decomposes the agent’s task into different sub- tasks. PROB-IRM uses a state-of-the-art inductive logic pro- gramming framework robust to noisy examples to learn RMs from noisy traces using the Bayesian posterior degree of be- liefs, thus ensuring robustness against inconsistencies. Piv- otal for the results is the interleaving between RM learning and policy learning: a new RM is learned whenever the RL agent generates a trace that is believed not to be accepted by the current RM. To speed up the training of the RL agent, PROB-IRM employs a probabilistic formulation of reward shaping that uses the posterior Bayesian beliefs derived from the traces. Our experimental analysis shows that PROB-IRM can learn (potentially imperfect) RMs from noisy traces and exploit them to train an RL agent to solve its tasks success- fully. Despite the complexity of learning the RM from noisy traces, agents trained with PROB-IRM perform comparably to agents provided with handcrafted RMs.