Related papers: Off-Policy Actor-Critic with Shared Experience Rep…
Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via…
Experience replay is crucial for off-policy reinforcement learning (RL) methods. By remembering and reusing the experiences from past different policies, experience replay significantly improves the training efficiency and stability of RL…
A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…
This work considers the problem of learning cooperative policies in multi-agent settings with partially observable and non-stationary environments without a communication channel. We focus on improving information sharing between agents and…
Training agents in cooperative settings offers the promise of AI agents able to interact effectively with humans (and other agents) in the real world. Multi-agent reinforcement learning (MARL) has the potential to achieve this goal,…
Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong baseline. Across diverse RL settings, we show that the…
Value-based methods of multi-agent reinforcement learning (MARL), especially the value decomposition methods, have been demonstrated on a range of challenging cooperative tasks. However, current methods pay little attention to the…
Motivated by the human-machine interaction such as training chatbots for improving customer satisfaction, we study human-guided human-machine interaction involving private information. We model this interaction as a two-player turn-based…
Automated vehicle control using reinforcement learning (RL) has attracted significant attention due to its potential to learn driving policies through environment interaction. However, RL agents often face training challenges in sample…
Multi-agent reinforcement learning (MARL) has attracted much research attention recently. However, unlike its single-agent counterpart, many theoretical and algorithmic aspects of MARL have not been well-understood. In this paper, we study…
Reinforcement learning in heterogeneous multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in homogeneous settings and simple benchmarks. In this work, we present an actor-critic…
We pursue a life-long learning approach to artificial intelligence that makes extensive use of reinforcement learning algorithms. We build on our prior work with general value functions (GVFs) and the Horde architecture. GVFs have been…
Reinforcement learning in partially observable domains is challenging due to the lack of observable state information. Thankfully, learning offline in a simulator with such state information is often possible. In particular, we propose a…
Off-policy model-free deep reinforcement learning methods using previously collected data can improve sample efficiency over on-policy policy gradient techniques. On the other hand, on-policy algorithms are often more stable and easier to…
Model-free reinforcement learning (RL) can be used to learn effective policies for complex tasks, such as Atari games, even from image observations. However, this typically requires very large amounts of interaction -- substantially more,…
ATARI is a suite of video games used by reinforcement learning (RL) researchers to test the effectiveness of the learning algorithm. Receiving only the raw pixels and the game score, the agent learns to develop sophisticated strategies,…
Despite the empirical success of the actor-critic algorithm, its theoretical understanding lags behind. In a broader context, actor-critic can be viewed as an online alternating update algorithm for bilevel optimization, whose convergence…
Experience replay is a core ingredient of modern deep reinforcement learning, yet its benefits in policy optimization are poorly understood beyond empirical heuristics. This paper develops a novel theoretical framework for experience replay…
We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named \textit{Diff-DAC}, with application to single-task and to average multitask reinforcement learning (MRL). Each agent has access to data from…
The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones. In the meta reinforcement learning literature much recent work has…