Consolidation via Policy Information Regularization in Deep RL for Multi-Agent Games

This paper introduces an information-theoretic constraint on learned policy complexity in the Multi-Agent Deep Deterministic Policy Gradient (MADDPG) reinforcement learning algorithm. Previous research with a related approach in continuous control experiments suggests that this method favors learning policies that are more robust to changing environment dynamics. The multi-agent game setting naturally requires this type of robustness, as other agents' policies change throughout learning, introducing a nonstationary environment. For this reason, recent methods in continual learning are compared to our approach, termed Capacity-Limited MADDPG. Results from experimentation in multi-agent cooperative and competitive tasks demonstrate that the capacity-limited approach is a good candidate for improving learning performance in these environments.

A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning

A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other agents that are also simultaneously learning. 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 nonstationarity in the distribution of experiences encountered. In this paper, we propose a novel meta-multiagent policy gradient theorem that directly accommodates for the non-stationary policy dynamics inherent to these multiagent settings. This is achieved by modeling our gradient updates to directly consider both an agent's own non-stationary policy dynamics and the non-stationary policy dynamics of other agents interacting with it in the environment. We find that our theoretically grounded approach provides a general solution to the multiagent learning problem, which inherently combines key aspects of previous state of the art approaches on this topic. We test our method on several multiagent benchmarks and demonstrate a more efficient ability to adapt to new agents as they learn than previous related approaches across the spectrum of mixed incentive, competitive, and cooperative environments.

Deep RL With Information Constrained Policies: Generalization in Continuous Control

Biological agents learn and act intelligently in spite of a highly limited capacity to process and store information. Many real-world problems involve continuous control, which represents a difficult task for artificial intelligence agents. In this paper we explore the potential learning advantages a natural constraint on information flow might confer onto artificial agents in continuous control tasks. We focus on the model-free reinforcement learning (RL) setting and formalize our approach in terms of an information-theoretic constraint on the complexity of learned policies. We show that our approach emerges in a principled fashion from the application of rate-distortion theory. We implement a novel Capacity-Limited Actor-Critic (CLAC) algorithm and situate it within a broader family of RL algorithms such as the Soft Actor Critic (SAC) and Mutual Information Reinforcement Learning (MIRL) algorithm. Our experiments using continuous control tasks show that compared to alternative approaches, CLAC offers improvements in generalization between training and modified test environments. This is achieved in the CLAC model while displaying the high sample efficiency of similar methods.

A Study of Compositional Generalization in Neural Models

Compositional and relational learning is a hallmark of human intelligence, but one which presents challenges for neural models. One difficulty in the development of such models is the lack of benchmarks with clear compositional and relational task structure on which to systematically evaluate them. In this paper, we introduce an environment called ConceptWorld, which enables the generation of images from compositional and relational concepts, defined using a logical domain specific language. We use it to generate images for a variety of compositional structures: 2x2 squares, pentominoes, sequences, scenes involving these objects, and other more complex concepts. We perform experiments to test the ability of standard neural architectures to generalize on relations with compositional arguments as the compositional depth of those arguments increases and under substitution. We compare standard neural networks such as MLP, CNN and ResNet, as well as state-of-the-art relational networks including WReN and PrediNet in a multi-class image classification setting. For simple problems, all models generalize well to close concepts but struggle with longer compositional chains. For more complex tests involving substitutivity, all models struggle, even with short chains. In highlighting these difficulties and providing an environment for further experimentation, we hope to encourage the development of models which are able to generalize effectively in compositional, relational domains.

Finding Macro-Actions with Disentangled Effects for Efficient Planning with the Goal-Count Heuristic

The difficulty of classical planning increases exponentially with search-tree depth. Heuristic search can make planning more efficient, but good heuristics often require domain-specific assumptions and may not generalize to new problems. Rather than treating the planning problem as fixed and carefully designing a heuristic to match it, we instead construct macro-actions that support efficient planning with the simple and general-purpose "goal-count" heuristic. Our approach searches for macro-actions that modify only a small number of state variables (we call this measure "entanglement"). We show experimentally that reducing entanglement exponentially decreases planning time with the goal-count heuristic. Our method discovers macro-actions with disentangled effects that dramatically improve planning efficiency for 15-puzzle and Rubik's cube, reliably solving each domain without prior knowledge, and solving Rubik's cube with orders of magnitude less data than competing approaches.

On the Role of Weight Sharing During Deep Option Learning

The options framework is a popular approach for building temporally extended actions in reinforcement learning. In particular, the option-critic architecture provides general purpose policy gradient theorems for learning actions from scratch that are extended in time. However, past work makes the key assumption that each of the components of option-critic has independent parameters. In this work we note that while this key assumption of the policy gradient theorems of option-critic holds in the tabular case, it is always violated in practice for the deep function approximation setting. We thus reconsider this assumption and consider more general extensions of option-critic and hierarchical option-critic training that optimize for the full architecture with each update. It turns out that not assuming parameter independence challenges a belief in prior work that training the policy over options can be disentangled from the dynamics of the underlying options. In fact, learning can be sped up by focusing the policy over options on states where options are actually likely to terminate. We put our new algorithms to the test in application to sample efficient learning of Atari games, and demonstrate significantly improved stability and faster convergence when learning long options.

Hierarchical Average Reward Policy Gradient Algorithms

Option-critic learning is a general-purpose reinforcement learning (RL) framework that aims to address the issue of long term credit assignment by leveraging temporal abstractions. However, when dealing with extended timescales, discounting future rewards can lead to incorrect credit assignments. In this work, we address this issue by extending the hierarchical option-critic policy gradient theorem for the average reward criterion. Our proposed framework aims to maximize the long-term reward obtained in the steady-state of the Markov chain defined by the agent's policy. Furthermore, we use an ordinary differential equation based approach for our convergence analysis and prove that the parameters of the intra-option policies, termination functions, and value functions, converge to their corresponding optimal values, with probability one. Finally, we illustrate the competitive advantage of learning options, in the average reward setting, on a grid-world environment with sparse rewards.

Routing Networks and the Challenges of Modular and Compositional Computation

Compositionality is a key strategy for addressing combinatorial complexity and the curse of dimensionality. Recent work has shown that compositional solutions can be learned and offer substantial gains across a variety of domains, including multi-task learning, language modeling, visual question answering, machine comprehension, and others. However, such models present unique challenges during training when both the module parameters and their composition must be learned jointly. In this paper, we identify several of these issues and analyze their underlying causes. Our discussion focuses on routing networks, a general approach to this problem, and examines empirically the interplay of these challenges and a variety of design decisions. In particular, we consider the effect of how the algorithm decides on module composition, how the algorithm updates the modules, and if the algorithm uses regularization.

Continual Learning with Self-Organizing Maps

Despite remarkable successes achieved by modern neural networks in a wide range of applications, these networks perform best in domain-specific stationary environments where they are trained only once on large-scale controlled data repositories. When exposed to non-stationary learning environments, current neural networks tend to forget what they had previously learned, a phenomena known as catastrophic forgetting. Most previous approaches to this problem rely on memory replay buffers which store samples from previously learned tasks, and use them to regularize the learning on new ones. This approach suffers from the important disadvantage of not scaling well to real-life problems in which the memory requirements become enormous. We propose a memoryless method that combines standard supervised neural networks with self-organizing maps to solve the continual learning problem. The role of the self-organizing map is to adaptively cluster the inputs into appropriate task contexts - without explicit labels - and allocate network resources accordingly. Thus, it selectively routes the inputs in accord with previous experience, ensuring that past learning is maintained and does not interfere with current learning. Out method is intuitive, memoryless, and performs on par with current state-of-the-art approaches on standard benchmarks.

Learning Hierarchical Teaching in Cooperative Multiagent Reinforcement Learning

Heterogeneous knowledge naturally arises among different agents in cooperative multiagent reinforcement learning. As such, learning can be greatly improved if agents can effectively pass their knowledge on to other agents. Existing work has demonstrated that peer-to-peer knowledge transfer, a process referred to as action advising, improves team-wide learning. In contrast to previous frameworks that advise at the level of primitive actions, we aim to learn high-level teaching policies that decide when and what high-level action (e.g., sub-goal) to advise a teammate. We introduce a new learning to teach framework, called hierarchical multiagent teaching (HMAT). The proposed framework solves difficulties faced by prior work on multiagent teaching when operating in domains with long horizons, delayed rewards, and continuous states/actions by leveraging temporal abstraction and deep function approximation. Our empirical evaluations show that HMAT accelerates team-wide learning progress in difficult environments that are more complex than those explored in previous work. HMAT also learns teaching policies that can be transferred to different teammates/tasks and can even teach teammates with heterogeneous action spaces.