Related papers: Unified Policy Value Decomposition for Rapid Adapt…
While bigger and deeper neural network architectures continue to advance the state-of-the-art for many computer vision tasks, real-world adoption of these networks is impeded by hardware and speed constraints. Conventional model compression…
Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence…
We present an optimised multi-modal dialogue agent for interactive learning of visually grounded word meanings from a human tutor, trained on real human-human tutoring data. Within a life-long interactive learning period, the agent, trained…
A major challenge in reinforcement learning (RL) is the design of agents that are able to generalize across tasks that share common dynamics. A viable solution is meta-reinforcement learning, which identifies common structures among past…
We study the problem of designing autonomous agents that can learn to cooperate effectively with a potentially suboptimal partner while having no access to the joint reward function. This problem is modeled as a cooperative episodic…
We investigate the combination of actor-critic reinforcement learning algorithms with uniform large-scale experience replay and propose solutions for two challenges: (a) efficient actor-critic learning with experience replay (b) stability…
While reinforcement learning methods have delivered remarkable results in a number of settings, generalization, i.e., the ability to produce policies that generalize in a reliable and systematic way, has remained a challenge. The problem of…
Recent advances have witnessed that value decomposed-based multi-agent reinforcement learning methods make an efficient performance in coordination tasks. Most current methods assume that agents can make communication to assist decisions,…
Training a game-playing reinforcement learning agent requires multiple interactions with the environment. Ignorant random exploration may cause a waste of time and resources. It's essential to alleviate such waste. As discussed in this…
We present a modular approach for learning policies for navigation over long planning horizons from language input. Our hierarchical policy operates at multiple timescales, where the higher-level master policy proposes subgoals to be…
We present an algorithm for learning an approximate action-value soft Q-function in the relative entropy regularised reinforcement learning setting, for which an optimal improved policy can be recovered in closed form. We use recent…
In many real-world multi-agent cooperative tasks, due to high cost and risk, agents cannot continuously interact with the environment and collect experiences during learning, but have to learn from offline datasets. However, the transition…
Multi-agent reinforcement learning (MARL) provides a promising paradigm for coordinating multi-agent systems (MAS). However, most existing methods rely on restrictive assumptions, such as a fixed number of agents and fully synchronous…
Deploying the idea of long-term cumulative return, reinforcement learning has shown remarkable performance in various fields. We propose a formulation of the landmark localization in 3D medical images as a reinforcement learning problem.…
Many instances of similar or almost-identical industrial machines or tools are often deployed at once, or in quick succession. For instance, a particular model of air compressor may be installed at hundreds of customers. Because these tools…
Control policy learning for modular robot locomotion has previously been limited to proprioceptive feedback and flat terrain. This paper develops policies for modular systems with vision traversing more challenging environments. These…
This paper proposes GProp, a deep reinforcement learning algorithm for continuous policies with compatible function approximation. The algorithm is based on two innovations. Firstly, we present a temporal-difference based method for…
Most reinforcement learning algorithms are inefficient for learning multiple tasks in complex robotic systems, where different tasks share a set of actions. In such environments a compound policy may be learnt with shared neural network…
We propose a novel framework for efficient parallelization of deep reinforcement learning algorithms, enabling these algorithms to learn from multiple actors on a single machine. The framework is algorithm agnostic and can be applied to…
Standard game theory explains cooperation in repeated games through conditional strategies such as Tit-for-Tat (TfT), but these require continuous computation that imposes physical costs on embodied agents. We propose a three-layer…