Deep Reinforcement Learning (DRL) and Deep Multi-agent Reinforcement Learning (MARL) have achieved significant success across a wide range of domains, such as game AI, autonomous vehicles, robotics and finance. However, DRL and deep MARL agents are widely known to be sample-inefficient and millions of interactions are usually needed even for relatively simple game settings, thus preventing the wide application in real-industry scenarios. One bottleneck challenge behind is the well-known exploration problem, i.e., how to efficiently explore the unknown environments and collect informative experiences that could benefit the policy learning most. In this paper, we conduct a comprehensive survey on existing exploration methods in DRL and deep MARL for the purpose of providing understandings and insights on the critical problems and solutions. We first identify several key challenges to achieve efficient exploration, which most of the exploration methods aim at addressing. Then we provide a systematic survey of existing approaches by classifying them into two major categories: uncertainty-oriented exploration and intrinsic motivation-oriented exploration. The essence of uncertainty-oriented exploration is to leverage the quantification of the epistemic and aleatoric uncertainty to derive efficient exploration. By contrast, intrinsic motivation-oriented exploration methods usually incorporate different reward agnostic information for intrinsic exploration guidance. Beyond the above two main branches, we also conclude other exploration methods which adopt sophisticated techniques but are difficult to be classified into the above two categories. In addition, we provide a comprehensive empirical comparison of exploration methods for DRL on a set of commonly used benchmarks. Finally, we summarize the open problems of exploration in DRL and deep MARL and point out a few future directions.

Discrete-continuous hybrid action space is a natural setting in many practical problems, such as robot control and game AI. However, most previous Reinforcement Learning (RL) works only demonstrate the success in controlling with either discrete or continuous action space, while seldom take into account the hybrid action space. One naive way to address hybrid action RL is to convert the hybrid action space into a unified homogeneous action space by discretization or continualization, so that conventional RL algorithms can be applied. However, this ignores the underlying structure of hybrid action space and also induces the scalability issue and additional approximation difficulties, thus leading to degenerated results. In this paper, we propose Hybrid Action Representation (HyAR) to learn a compact and decodable latent representation space for the original hybrid action space. HyAR constructs the latent space and embeds the dependence between discrete action and continuous parameter via an embedding table and conditional Variantional Auto-Encoder (VAE). To further improve the effectiveness, the action representation is trained to be semantically smooth through unsupervised environmental dynamics prediction. Finally, the agent then learns its policy with conventional DRL algorithms in the learned representation space and interacts with the environment by decoding the hybrid action embeddings to the original action space. We evaluate HyAR in a variety of environments with discrete-continuous action space. The results demonstrate the superiority of HyAR when compared with previous baselines, especially for high-dimensional action spaces.

The value function lies in the heart of Reinforcement Learning (RL), which defines the long-term evaluation of a policy in a given state. In this paper, we propose Policy-extended Value Function Approximator (PeVFA) which extends the conventional value to be not only a function of state but also an explicit policy representation. Such an extension enables PeVFA to preserve values of multiple policies in contrast to a conventional one with limited capacity for only one policy, inducing the new characteristic of \emph{value generalization among policies}. From both the theoretical and empirical lens, we study value generalization along the policy improvement path (called local generalization), from which we derive a new form of Generalized Policy Iteration with PeVFA to improve the conventional learning process. Besides, we propose a framework to learn the representation of an RL policy, studying several different approaches to learn an effective policy representation from policy network parameters and state-action pairs through contrastive learning and action prediction. In our experiments, Proximal Policy Optimization (PPO) with PeVFA significantly outperforms its vanilla counterpart in MuJoCo continuous control tasks, demonstrating the effectiveness of value generalization offered by PeVFA and policy representation learning.

Context, the embedding of previous collected trajectories, is a powerful construct for Meta-Reinforcement Learning (Meta-RL) algorithms. By conditioning on an effective context, Meta-RL policies can easily generalize to new tasks within a few adaptation steps. We argue that improving the quality of context involves answering two questions: 1. How to train a compact and sufficient encoder that can embed the task-specific information contained in prior trajectories? 2. How to collect informative trajectories of which the corresponding context reflects the specification of tasks? To this end, we propose a novel Meta-RL framework called CCM (Contrastive learning augmented Context-based Meta-RL). We first focus on the contrastive nature behind different tasks and leverage it to train a compact and sufficient context encoder. Further, we train a separate exploration policy and theoretically derive a new information-gain-based objective which aims to collect informative trajectories in a few steps. Empirically, we evaluate our approaches on common benchmarks as well as several complex sparse-reward environments. The experimental results show that CCM outperforms state-of-the-art algorithms by addressing previously mentioned problems respectively.

Meta reinforcement learning (meta-RL) is able to accelerate the acquisition of new tasks by learning from past experience. Current meta-RL methods usually learn to adapt to new tasks by directly optimizing the parameters of policies over primitive actions. However, for complex tasks which requires sophisticated control strategies, it would be quite inefficient to to directly learn such a meta-policy. Moreover, this problem can become more severe and even fail in spare reward settings, which is quite common in practice. To this end, we propose a new meta-RL algorithm called meta goal-generation for hierarchical RL (MGHRL) by leveraging hierarchical actor-critic framework. Instead of directly generate policies over primitive actions for new tasks, MGHRL learns to generate high-level meta strategies over subgoals given past experience and leaves the rest of how to achieve subgoals as independent RL subtasks. Our empirical results on several challenging simulated robotics environments show that our method enables more efficient and effective meta-learning from past experience and outperforms state-of-the-art meta-RL and Hierarchical-RL methods in sparse reward settings.

Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates. Value estimation heavily depends on the stochasticity of environmental dynamics and the quality of reward signals. In this paper, we propose a two-step understanding of value estimation from the perspective of future prediction, through decomposing the value function into a reward-independent future dynamics part and a policy-independent trajectory return part. We then derive a practical deep RL algorithm from the above decomposition, consisting of a convolutional trajectory representation model, a conditional variational dynamics model to predict the expected representation of future trajectory and a convex trajectory return model that maps a trajectory representation to its return. Our algorithm is evaluated in MuJoCo continuous control tasks and shows superior results under both common settings and delayed reward settings.

Deep Reinforcement Learning (DRL) has been applied to address a variety of cooperative multi-agent problems with either discrete action spaces or continuous action spaces. However, to the best of our knowledge, no previous work has ever succeeded in applying DRL to multi-agent problems with discrete-continuous hybrid (or parameterized) action spaces which is very common in practice. Our work fills this gap by proposing two novel algorithms: Deep Multi-Agent Parameterized Q-Networks (Deep MAPQN) and Deep Multi-Agent Hierarchical Hybrid Q-Networks (Deep MAHHQN). We follow the centralized training but decentralized execution paradigm: different levels of communication between different agents are used to facilitate the training process, while each agent executes its policy independently based on local observations during execution. Our empirical results on several challenging tasks (simulated RoboCup Soccer and game Ghost Story) show that both Deep MAPQN and Deep MAHHQN are effective and significantly outperform existing independent deep parameterized Q-learning method.

Despite deep reinforcement learning has recently achieved great successes, however in multiagent environments, a number of challenges still remain. Multiagent reinforcement learning (MARL) is commonly considered to suffer from the problem of non-stationary environments and exponentially increasing policy space. It would be even more challenging to learn effective policies in circumstances where the rewards are sparse and delayed over long trajectories. In this paper, we study Hierarchical Deep Multiagent Reinforcement Learning (hierarchical deep MARL) in cooperative multiagent problems with sparse and delayed rewards, where efficient multiagent learning methods are desperately needed. We decompose the original MARL problem into hierarchies and investigate how effective policies can be learned hierarchically in synchronous/asynchronous hierarchical MARL frameworks. Several hierarchical deep MARL architectures, i.e., Ind-hDQN, hCom and hQmix, are introduced for different learning paradigms. Moreover, to alleviate the issues of sparse experiences in high-level learning and non-stationarity in multiagent settings, we propose a new experience replay mechanism, named as Augmented Concurrent Experience Replay (ACER). We empirically demonstrate the effects and efficiency of our approaches in several classic Multiagent Trash Collection tasks, as well as in an extremely challenging team sports game, i.e., Fever Basketball Defense.

Multiagent coordination in cooperative multiagent systems (MASs) has been widely studied in both fixed-agent repeated interaction setting and the static social learning framework. However, two aspects of dynamics in real-world multiagent scenarios are currently missing in existing works. First, the network topologies can be dynamic where agents may change their connections through rewiring during the course of interactions. Second, the game matrix between each pair of agents may not be static and usually not known as a prior. Both the network dynamic and game uncertainty increase the coordination difficulty among agents. In this paper, we consider a multiagent dynamic social learning environment in which each agent can choose to rewire potential partners and interact with randomly chosen neighbors in each round. We propose an optimal rewiring strategy for agents to select most beneficial peers to interact with for the purpose of maximizing the accumulated payoff in repeated interactions. We empirically demonstrate the effectiveness and robustness of our approach through comparing with benchmark strategies. The performance of three representative learning strategies under our social learning framework with our optimal rewiring is investigated as well.