Related papers: Learning to Explore with Meta-Policy Gradient
This paper deploys the Deep Deterministic Policy Gradient (DDPG) algorithm for longitudinal and lateral control of a simulated car to solve a path following task. The DDPG agent was implemented using PyTorch and trained and evaluated on a…
Deep learning is currently reaching outstanding performances on different tasks, including image classification, especially when using large neural networks. The success of these models is tributary to the availability of large collections…
Developing agents that can perform challenging complex tasks is the goal of reinforcement learning. The model-free reinforcement learning has been considered as a feasible solution. However, the state of the art research has been to develop…
Policy gradient methods hold great potential for solving complex continuous control tasks. Still, their training efficiency can be improved by exploiting structure within the optimization problem. Recent work indicates that supervised…
Existing on-policy imitation learning algorithms, such as DAgger, assume access to a fixed supervisor. However, there are many settings where the supervisor may evolve during policy learning, such as a human performing a novel task or an…
We apply diffusion strategies to develop a fully-distributed cooperative reinforcement learning algorithm in which agents in a network communicate only with their immediate neighbors to improve predictions about their environment. The…
Learning optimal behavior from existing data is one of the most important problems in Reinforcement Learning (RL). This is known as "off-policy control" in RL where an agent's objective is to compute an optimal policy based on the data…
Offline policy learning aims to discover decision-making policies from previously-collected datasets without additional online interactions with the environment. As the training dataset is fixed, its quality becomes a crucial determining…
Real-world applications require RL algorithms to act safely. During learning process, it is likely that the agent executes sub-optimal actions that may lead to unsafe/poor states of the system. Exploration is particularly brittle in…
Guided policy search algorithms can be used to optimize complex nonlinear policies, such as deep neural networks, without directly computing policy gradients in the high-dimensional parameter space. Instead, these methods use supervised…
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…
In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important…
Deep reinforcement learning (DRL) faces significant challenges in addressing the hard-exploration problems in tasks with sparse or deceptive rewards and large state spaces. These challenges severely limit the practical application of DRL.…
In many real world applications, reinforcement learning agents have to optimize multiple objectives while following certain rules or satisfying a list of constraints. Classical methods based on reward shaping, i.e. a weighted combination of…
Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not…
In this work, we propose Behavior-Guided Actor-Critic (BAC), an off-policy actor-critic deep RL algorithm. BAC mathematically formulates the behavior of the policy through autoencoders by providing an accurate estimation of how frequently…
In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features…
Sample inefficiency is a long-lasting problem in reinforcement learning (RL). The state-of-the-art estimates the optimal action values while it usually involves an extensive search over the state-action space and unstable optimization.…
On-policy deep reinforcement learning remains a dominant paradigm for continuous control, yet standard implementations rely on Gaussian actors and relatively shallow MLP policies, often leading to brittle optimization when gradients are…
Many cooperative multi-agent problems require agents to learn individual tasks while contributing to the collective success of the group. This is a challenging task for current state-of-the-art multi-agent reinforcement algorithms that are…