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, the choice of the potential function is critical for this technique to be effective. Additionally, RL techniques are usually constrained to use a finite horizon for computational limitations. This introduces a bias when using PBRS, thus adding an additional layer of complexity. In this paper, we leverage abstractions to automatically produce a "good" potential function. We analyse the bias induced by finite horizons in the context of PBRS producing novel insights. Finally, to asses sample efficiency and performance impact, we evaluate our approach on four environments including a goal-oriented navigation task and three Arcade Learning Environments (ALE) games demonstrating that we can reach the same level of performance as CNN-based solutions with a simple fully-connected network.
This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL) that combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks. The proposed method helps deal with the non-Markovian nature of the rewards in partially observable environments and improves the interpretability of the learnt policies required to complete the cooperative task. The RMs associated with each sub-task are learnt in a decentralised manner and then used to guide the behaviour of each agent. By doing so, the complexity of a cooperative multi-agent problem is reduced, allowing for more effective learning. The results suggest that our approach is a promising direction for future research in MARL, especially in complex environments with large state spaces and multiple agents.
Reinforcement Learning (RL) algorithms are known to scale poorly to environments with many available actions, requiring numerous samples to learn an optimal policy. The traditional approach of considering the same fixed action space in every possible state implies that the agent must understand, while also learning to maximize its reward, to ignore irrelevant actions such as $\textit{inapplicable actions}$ (i.e. actions that have no effect on the environment when performed in a given state). Knowing this information can help reduce the sample complexity of RL algorithms by masking the inapplicable actions from the policy distribution to only explore actions relevant to finding an optimal policy. This is typically done in an ad-hoc manner with hand-crafted domain logic added to the RL algorithm. In this paper, we propose a more systematic approach to introduce this knowledge into the algorithm. We (i) standardize the way knowledge can be manually specified to the agent; and (ii) present a new framework to autonomously learn these state-dependent action constraints jointly with the policy. We show experimentally that learning inapplicable actions greatly improves the sample efficiency of the algorithm by providing a reliable signal to mask out irrelevant actions. Moreover, we demonstrate that thanks to the transferability of the knowledge acquired, it can be reused in other tasks to make the learning process more efficient.
We study a game between liquidity provider and liquidity taker agents interacting in an over-the-counter market, for which the typical example is foreign exchange. We show how a suitable design of parameterized families of reward functions coupled with associated shared policy learning constitutes an efficient solution to this problem. Precisely, we show that our deep-reinforcement-learning-driven agents learn emergent behaviors relative to a wide spectrum of incentives encompassing profit-and-loss, optimal execution and market share, by playing against each other. In particular, we find that liquidity providers naturally learn to balance hedging and skewing as a function of their incentives, where the latter refers to setting their buy and sell prices asymmetrically as a function of their inventory. We further introduce a novel RL-based calibration algorithm which we found performed well at imposing constraints on the game equilibrium, both on toy and real market data.
Agent based modeling (ABM) is a computational approach to modeling complex systems by specifying the behavior of autonomous decision-making components or agents in the system and allowing the system dynamics to emerge from their interactions. Recent advances in the field of Multi-agent reinforcement learning (MARL) have made it feasible to learn the equilibrium of complex environments where multiple agents learn at the same time - opening up the possibility of building ABMs where agent behaviors are learned and system dynamics can be analyzed. However, most ABM frameworks are not RL-native, in that they do not offer concepts and interfaces that are compatible with the use of MARL to learn agent behaviors. In this paper, we introduce a new framework, Phantom, to bridge the gap between ABM and MARL. Phantom is an RL-driven framework for agent-based modeling of complex multi-agent systems such as economic systems and markets. To enable this, the framework provides tools to specify the ABM in MARL-compatible terms - including features to encode dynamic partial observability, agent utility / reward functions, heterogeneity in agent preferences or types, and constraints on the order in which agents can act (e.g. Stackelberg games, or complex turn-taking environments). In this paper, we present these features, their design rationale and show how they were used to model and simulate Over-The-Counter (OTC) markets.
In this paper, we evaluate the use of Reinforcement Learning (RL) to solve a classic combinatorial optimization problem: the Capacitated Vehicle Routing Problem (CVRP). We formalize this problem in the RL framework and compare two of the most promising RL approaches with traditional solving techniques on a set of benchmark instances. We measure the different approaches with the quality of the solution returned and the time required to return it. We found that despite not returning the best solution, the RL approach has many advantages over traditional solvers. First, the versatility of the framework allows the resolution of more complex combinatorial problems. Moreover, instead of trying to solve a specific instance of the problem, the RL algorithm learns the skills required to solve the problem. The trained policy can then quasi instantly provide a solution to an unseen problem without having to solve it from scratch. Finally, the use of trained models makes the RL solver by far the fastest, and therefore make this approach more suited for commercial use where the user experience is paramount. Techniques like Knowledge Transfer can also be used to improve the training efficiency of the algorithm and help solve bigger and more complex problems.
We present a new financial framework where two families of RL-based agents representing the Liquidity Providers and Liquidity Takers learn simultaneously to satisfy their objective. Thanks to a parametrized reward formulation and the use of Deep RL, each group learns a shared policy able to generalize and interpolate over a wide range of behaviors. This is a step towards a fully RL-based market simulator replicating complex market conditions particularly suited to study the dynamics of the financial market under various scenarios.