Miao Liu

Junkyu Lee, Michael Katz, Don Joven Agravante et al. · ibm-research

Two common approaches to sequential decision-making are AI planning (AIP) and reinforcement learning (RL). Each has strengths and weaknesses. AIP is interpretable, easy to integrate with symbolic knowledge, and often efficient, but requires an up-front logical domain specification and is sensitive to noise; RL only requires specification of rewards and is robust to noise but is sample inefficient and not easily supplied with external knowledge. We propose an integrative approach that combines high-level planning with RL, retaining interpretability, transfer, and efficiency, while allowing for robust learning of the lower-level plan actions. Our approach defines options in hierarchical reinforcement learning (HRL) from AIP operators by establishing a correspondence between the state transition model of AI planning problem and the abstract state transition system of a Markov Decision Process (MDP). Options are learned by adding intrinsic rewards to encourage consistency between the MDP and AIP transition models. We demonstrate the benefit of our integrated approach by comparing the performance of RL and HRL algorithms in both MiniGrid and N-rooms environments, showing the advantage of our method over the existing ones.

Hadi Nekoei, Xutong Zhao, Janarthanan Rajendran et al.

Cooperative Multi-agent Reinforcement Learning (MARL) algorithms with Zero-Shot Coordination (ZSC) have gained significant attention in recent years. ZSC refers to the ability of agents to coordinate zero-shot (without additional interaction experience) with independently trained agents. While ZSC is crucial for cooperative MARL agents, it might not be possible for complex tasks and changing environments. Agents also need to adapt and improve their performance with minimal interaction with other agents. In this work, we show empirically that state-of-the-art ZSC algorithms have poor performance when paired with agents trained with different learning methods, and they require millions of interaction samples to adapt to these new partners. To investigate this issue, we formally defined a framework based on a popular cooperative multi-agent game called Hanabi to evaluate the adaptability of MARL methods. In particular, we created a diverse set of pre-trained agents and defined a new metric called adaptation regret that measures the agent's ability to efficiently adapt and improve its coordination performance when paired with some held-out pool of partners on top of its ZSC performance. After evaluating several SOTA algorithms using our framework, our experiments reveal that naive Independent Q-Learning (IQL) agents in most cases adapt as quickly as the SOTA ZSC algorithm Off-Belief Learning (OBL). This finding raises an interesting research question: How to design MARL algorithms with high ZSC performance and capability of fast adaptation to unseen partners. As a first step, we studied the role of different hyper-parameters and design choices on the adaptability of current MARL algorithms. Our experiments show that two categories of hyper-parameters controlling the training data diversity and optimization process have a significant impact on the adaptability of Hanabi agents.

Arjun V Sudhakar, Hadi Nekoei, Mathieu Reymond et al.

Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions. However, these systems are unable to perform well on any other setting than the one they have been trained on, and struggle to successfully cooperate with unfamiliar collaborators. This is particularly visible in the Hanabi benchmark, a popular 2-to-5 player cooperative card-game which requires complex reasoning and precise assistance to other agents. Current MARL agents for Hanabi can only learn one specific game-setting (e.g., 2-player games), and play with the same algorithmic agents. This is in stark contrast to humans, who can quickly adjust their strategies to work with unfamiliar partners or situations. In this paper, we introduce Recurrent Replay Relevance Distributed DQN (R3D2), a generalist agent for Hanabi, designed to overcome these limitations. We reformulate the task using text, as language has been shown to improve transfer. We then propose a distributed MARL algorithm that copes with the resulting dynamic observation- and action-space. In doing so, our agent is the first that can play all game settings concurrently, and extend strategies learned from one setting to other ones. As a consequence, our agent also demonstrates the ability to collaborate with different algorithmic agents -- agents that are themselves unable to do so. The implementation code is available at: $\href{https://github.com/chandar-lab/R3D2-A-Generalist-Hanabi-Agent}{R3D2-A-Generalist-Hanabi-Agent}$

Ronny Luss, Amit Dhurandhar, Miao Liu

Many works in explainable AI have focused on explaining black-box classification models. Explaining deep reinforcement learning (RL) policies in a manner that could be understood by domain users has received much less attention. In this paper, we propose a novel perspective to understanding RL policies based on identifying important states from automatically learned meta-states. The key conceptual difference between our approach and many previous ones is that we form meta-states based on locality governed by the expert policy dynamics rather than based on similarity of actions, and that we do not assume any particular knowledge of the underlying topology of the state space. Theoretically, we show that our algorithm to find meta-states converges and the objective that selects important states from each meta-state is submodular leading to efficient high quality greedy selection. Experiments on four domains (four rooms, door-key, minipacman, and pong) and a carefully conducted user study illustrate that our perspective leads to better understanding of the policy. We conjecture that this is a result of our meta-states being more intuitive in that the corresponding important states are strong indicators of tractable intermediate goals that are easier for humans to interpret and follow.

Marwa Abdulhai, Dong-Ki Kim, Matthew Riemer et al.

Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration. One promising approach that learns these options end-to-end is the option-critic (OC) framework. We examine and show in this paper that OC does not decompose a problem into simpler sub-problems, but instead increases the size of the search over policy space with each option considering the entire state space during learning. This issue can result in practical limitations of this method, including sample inefficient learning. To address this problem, we introduce Context-Specific Representation Abstraction for Deep Option Learning (CRADOL), a new framework that considers both temporal abstraction and context-specific representation abstraction to effectively reduce the size of the search over policy space. Specifically, our method learns a factored belief state representation that enables each option to learn a policy over only a subsection of the state space. We test our method against hierarchical, non-hierarchical, and modular recurrent neural network baselines, demonstrating significant sample efficiency improvements in challenging partially observable environments.

Dong-Ki Kim, Miao Liu, Matthew Riemer et al.

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively non-stationary due to the changing policies of other agents. Moreover, each agent is itself constantly learning, leading to natural non-stationarity in the distribution of experiences encountered. In this paper, we propose a novel meta-multiagent policy gradient theorem that directly accounts for the non-stationary policy dynamics inherent to multiagent learning settings. This is achieved by modeling our gradient updates to consider both an agent's own non-stationary policy dynamics and the non-stationary policy dynamics of other agents in the environment. We show that our theoretically grounded approach provides a general solution to the multiagent learning problem, which inherently comprises all key aspects of previous state of the art approaches on this topic. We test our method on a diverse suite of multiagent benchmarks and demonstrate a more efficient ability to adapt to new agents as they learn than baseline methods across the full spectrum of mixed incentive, competitive, and cooperative domains.

Matthew Riemer, Ignacio Cases, Robert Ajemian et al.

Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off between transfer and interference that can be optimized by enforcing gradient alignment across examples. We then propose a new algorithm, Meta-Experience Replay (MER), that directly exploits this view by combining experience replay with optimization based meta-learning. This method learns parameters that make interference based on future gradients less likely and transfer based on future gradients more likely. We conduct experiments across continual lifelong supervised learning benchmarks and non-stationary reinforcement learning environments demonstrating that our approach consistently outperforms recently proposed baselines for continual learning. Our experiments show that the gap between the performance of MER and baseline algorithms grows both as the environment gets more non-stationary and as the fraction of the total experiences stored gets smaller.

Matthew Riemer, Miao Liu, Gerald Tesauro

Building systems that autonomously create temporal abstractions from data is a key challenge in scaling learning and planning in reinforcement learning. One popular approach for addressing this challenge is the options framework (Sutton et al., 1999). However, only recently in (Bacon et al., 2017) was a policy gradient theorem derived for online learning of general purpose options in an end to end fashion. In this work, we extend previous work on this topic that only focuses on learning a two-level hierarchy including options and primitive actions to enable learning simultaneously at multiple resolutions in time. We achieve this by considering an arbitrarily deep hierarchy of options where high level temporally extended options are composed of lower level options with finer resolutions in time. We extend results from (Bacon et al., 2017) and derive policy gradient theorems for a deep hierarchy of options. Our proposed hierarchical option-critic architecture is capable of learning internal policies, termination conditions, and hierarchical compositions over options without the need for any intrinsic rewards or subgoals. Our empirical results in both discrete and continuous environments demonstrate the efficiency of our framework.