An official website of the United States government
Multiagent teams have been shown to be effective in many domains that require coordination among team members. However, finding valuable joint-actions becomes increasingly difficult in tightly-coupled domains where each agent’s performance depends on the actions of many other agents. Reward shaping partially addresses this challenge by deriving more “tuned" rewards to provide agents with additional feedback, but this approach still relies on agents ran- domly discovering suitable joint-actions. In this work, we introduce Counterfactual Agent Suggestions (CAS) as a method for injecting knowledge into an agent’s learning process within the confines of existing reward structures. We show that CAS enables agent teams to converge towards desired behaviors more reliably. We also show that improvement in team performance in the presence of suggestions extends to large teams and tightly-coupled domains.
more »
« less
Gaussian Processes as Multiagent Reward Models
In multiagent problems that require complex joint actions, reward shaping methods yield good behavior by incentivizing the agents’ potentially valuable actions. However, reward shaping often requires access to the functional form of the reward function and the global state of the system. In this work, we introduce the Exploratory Gaussian Reward (EGR), a new reward model that creates optimistic stepping stone rewards linking the agents potentially good actions to the desired joint action. EGR models the system reward as a Gaussian Process to leverage the inherent uncertainty in reward estimates that push agents to explore unobserved state space. In the tightly coupled rover coordination problem, we show that EGR significantly outperforms a neural network approximation baseline and is comparable to the system with access to the functional form of the global reward. Finally, we demonstrate how EGR improves performance over other reward shaping methods by forcing agents to explore and escape local optima.
more »
« less
- Award ID(s):
- 1815886
- PAR ID:
- 10197809
- Date Published:
- Journal Name:
- AAMAS Conference proceedings
- ISSN:
- 2523-5699
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Interactive reinforcement learning (IRL) agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal that’s either positive or negative. While informative, this information can be difficult to generalize on its own. In this work, we explore how natural language advice can be used to provide a richer feedback signal to a reinforcement learning agent by extending policy shaping, a well-known IRL technique. Usually policy shaping employs a human feedback policy to help an agent to learn more about how to achieve its goal. In our case, we replace this human feedback policy with policy generated based on natural language advice. We aim to inspect if the generated natural language reasoning provides support to a deep RL agent to decide its actions successfully in any given environment. So, we design our model with three networks: first one is the experience driven, next is the advice generator and third one is the advice driven. While the experience driven RL agent chooses its actions being influenced by the environmental reward, the advice driven neural network with generated feedback by the advice generator for any new state selects its actions to assist the RL agent to better policy shaping.more » « less
-
Silva, S; Paquete, L (Ed.)Coevolving teams of agents promises effective solutions for many coordination tasks such as search and rescue missions or deep ocean exploration. Good team performance in such domains generally relies on agents discovering complex joint policies, which is particularly difficult when the fitness functions are sparse (where many joint policies return the same or even zero fitness values). In this paper, we introduce Novelty Seeking Multiagent Evolutionary Reinforcement Learning (NS-MERL), which enables agents to more efficiently explore their joint strategy space. The key insight of NS-MERL is to promote good exploratory behaviors for individual agents using a dense, novelty-based fitness function. Though the overall team-level performance is still evaluated via a sparse fitness function, agents using NS-MERL more efficiently explore their joint action space and more readily discover good joint policies. Our results in complex coordination tasks show that teams of agents trained with NS-MERL perform significantly better than agents trained solely with task-specific fitnesses.more » « less
-
null (Ed.)Learning in tightly coupled multiagent settings with sparse rewards is challenging because multiple agents must reach the goal state simultaneously for the team to receive a reward. This is even more challenging under temporal coupling constraints - where agents need to sequentially complete different components of a task in a particular order. Here, a single local reward is inadequate for learning an effective policy. We introduce MADyS, Multiagent Learning via Dynamic Skill Selection, a bi-level optimization framework that learns to dynamically switch between multiple local skills to optimize sparse team objectives. MADyS adopts fast policy gradients to learn local skills using local rewards and an evolutionary algorithm to optimize the sparse team objective by recruiting the most optimal skill at any given time. This eliminates the need to generate a single dense reward via reward shaping or other mixing functions. In environments with both spatial and temporal coupling requirements, we outperform prior methods and provides intuitive visualizations of its skill switching strategy.more » « less
-
In distributed optimization schemes consisting of a group of agents connected to a central coordinator, the optimization algorithm often involves the agents solving private local sub-problems and exchanging data frequently with the coordinator to solve the global distributed problem. In those cases, the query-response mechanism usually causes excessive communication costs to the system, necessitating communication reduction in scenarios where communication is costly. Integrating Gaussian processes (GP) as a learning component to the Alternating Direction Method of Multipliers (ADMM) has proven effective in learning each agent’s local proximal operator to reduce the required communication exchange. A key element for integrating GP into the ADMM algorithm is the querying mechanism upon which the coordinator decides when communication with an agent is required. In this paper, we formulate a general querying decision framework as an optimization problem that balances reducing the communication cost and decreasing the prediction error. Under this framework, we propose a joint query strategy that takes into account the joint statistics of the query and ADMM variables and the total communication cost of all agents in the presence of uncertainty caused by the GP regression. In addition, we derive three different decision mechanisms that simplify the general framework by making the communication decision for each agent individually. We integrate multiple measures to quantify the trade-off between the communication cost reduction and the optimization solution’s accuracy/optimality. The proposed methods can achieve significant communication reduction and good optimization solution accuracy for distributed optimization, as demonstrated by extensive simulations of a distributed sharing problem.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
