相关论文: Terminal Prediction as an Auxiliary Task for Deep …

We consider scenarios from the real-time strategy game StarCraft as new benchmarks for reinforcement learning algorithms. We propose micromanagement tasks, which present the problem of the short-term, low-level control of army members…

The exploration mechanism used by a Deep Reinforcement Learning (RL) agent plays a key role in determining its sample efficiency. Thus, improving over random exploration is crucial to solve long-horizon tasks with sparse rewards. We propose…

In this paper, we study the problem of learning to satisfy temporal logic specifications with a group of agents in an unknown environment, which may exhibit probabilistic behaviour. From a learning perspective these specifications provide a…

Reinforcement learning is concerned with identifying reward-maximizing behaviour policies in environments that are initially unknown. State-of-the-art reinforcement learning approaches, such as deep Q-networks, are model-free and learn to…

The asynchronous nature of the state-of-the-art reinforcement learning algorithms such as the Asynchronous Advantage Actor-Critic algorithm, makes them exceptionally suitable for CPU computations. However, given the fact that deep…

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

Chemotherapy dose optimization can be formulated as a dynamic treatment regime, requiring sequential decisions under uncertainty that must balance tumor suppression against toxicity. However, most reinforcement learning approaches assume…

In artificial intelligence, we often specify tasks through a reward function. While this works well in some settings, many tasks are hard to specify this way. In deep reinforcement learning, for example, directly specifying a reward as a…

Risk is 6 player game with significant randomness and a large game-tree complexity which poses a challenge to creating an agent to play the game effectively. Previous AIs focus on creating high-level handcrafted features determine agent…

Policy gradient methods in actor-critic reinforcement learning (RL) have become perhaps the most promising approaches to solving continuous optimal control problems. However, the trial-and-error nature of RL and the inherent randomness…

Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in…

Stochastic games are a popular framework for studying multi-agent reinforcement learning (MARL). Recent advances in MARL have focused primarily on games with finitely many states. In this work, we study multi-agent learning in stochastic…

Multi-agent reinforcement learning has received significant interest in recent years notably due to the advancements made in deep reinforcement learning which have allowed for the developments of new architectures and learning algorithms.…

This paper develops a policy learning method for tuning a pre-trained policy to adapt to additional tasks without altering the original task. A method named Adaptive Policy Gradient (APG) is proposed in this paper, which combines Bellman's…

We present a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage ActorCritic (BA3C). We show that using the Adam…

Temporal-Difference (TD) learning is a general and very useful tool for estimating the value function of a given policy, which in turn is required to find good policies. Generally speaking, TD learning updates states whenever they are…

Tasks with complex temporal structures and long horizons pose a challenge for reinforcement learning agents due to the difficulty in specifying the tasks in terms of reward functions as well as large variances in the learning signals. We…

We study Reinforcement Learning for partially observable dynamical systems using function approximation. We propose a new \textit{Partially Observable Bilinear Actor-Critic framework}, that is general enough to include models such as…

Existing action detection algorithms usually generate action proposals through an extensive search over the video at multiple temporal scales, which brings about huge computational overhead and deviates from the human perception procedure.…

Deep neural networks have demonstrated their capability to learn control policies for a variety of tasks. However, these neural network-based policies have been shown to be susceptible to exploitation by adversarial agents. Therefore, there…