Deep Reinforcement Learning in Linear Discrete Action Spaces

2020 ◽  
Author(s):  
Wouter van Heeswijk ◽  
Han La Poutre
Keyword(s):  
Reinforcement Learning ◽  
Discrete Action ◽  
Action Spaces

scholarly journals MULTIPOLAR: Multi-Source Policy Aggregation for Transfer Reinforcement Learning between Diverse Environmental Dynamics

2020 ◽  
Author(s):  
Mohammadamin Barekatain ◽  
Ryo Yonetani ◽  
Masashi Hamaya
Keyword(s):  
Reinforcement Learning ◽  
Task Performance ◽  
Experimental Evaluation ◽  
Control Problems ◽  
Target Task ◽  
Learning Efficiency ◽  
Simulated Environments ◽  
Discrete Action ◽  
Key Techniques ◽  
Action Spaces

Transfer reinforcement learning (RL) aims at improving the learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks. However, it remains challenging to transfer knowledge between different environmental dynamics without having access to the source environments. In this work, we explore a new challenge in transfer RL, where only a set of source policies collected under diverse unknown dynamics is available for learning a target task efficiently. To address this problem, the proposed approach, MULTI-source POLicy AggRegation (MULTIPOLAR), comprises two key techniques. We learn to aggregate the actions provided by the source policies adaptively to maximize the target task performance. Meanwhile, we learn an auxiliary network that predicts residuals around the aggregated actions, which ensures the target policy's expressiveness even when some of the source policies perform poorly. We demonstrated the effectiveness of MULTIPOLAR through an extensive experimental evaluation across six simulated environments ranging from classic control problems to challenging robotics simulations, under both continuous and discrete action spaces. The demo videos and code are available on the project webpage: https://omron-sinicx.github.io/multipolar/.

scholarly journals Deep Multi-Agent Reinforcement Learning with Discrete-Continuous Hybrid Action Spaces

2019 ◽  
Author(s):  
Haotian Fu ◽  
Hongyao Tang ◽  
Jianye Hao ◽  
Zihan Lei ◽  
Yingfeng Chen ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Continuous Action ◽  
Q Learning ◽  
Challenging Tasks ◽  
Discrete Action ◽  
Multi Agent ◽  
Decentralized Execution ◽  
Novel Algorithms ◽  
Action Spaces ◽  
Different Levels

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.

scholarly journals Ubiquitous Distributed Deep Reinforcement Learning at the Edge: Analyzing Byzantine Agents in Discrete Action Spaces

2020 ◽  
Vol 177 ◽  
pp. 324-329
Author(s):  
Wenshuai Zhao ◽  
Jorge Peña Queralta ◽  
Li Qingqing ◽  
Tomi Westerlund
Keyword(s):  
Reinforcement Learning ◽  
Discrete Action ◽  
Action Spaces

scholarly journals Vision Based Drone Obstacle Avoidance by Deep Reinforcement Learning

AI ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 366-382
Author(s):  
Zhihan Xue ◽  
Tad Gonsalves
Keyword(s):  
Reinforcement Learning ◽  
Supervised Learning ◽  
Obstacle Avoidance ◽  
Image Data ◽  
Depth Map ◽  
Training Environment ◽  
Time To Build ◽  
Discrete Action ◽  
Single Dataset ◽  
Action Spaces

Research on autonomous obstacle avoidance of drones has recently received widespread attention from researchers. Among them, an increasing number of researchers are using machine learning to train drones. These studies typically adopt supervised learning or reinforcement learning to train the networks. Supervised learning has a disadvantage in that it takes a significant amount of time to build the datasets, because it is difficult to cover the complex and changeable drone flight environment in a single dataset. Reinforcement learning can overcome this problem by using drones to learn data in the environment. However, the current research results based on reinforcement learning are mainly focused on discrete action spaces. In this way, the movement of drones lacks precision and has somewhat unnatural flying behavior. This study aims to use the soft-actor-critic algorithm to train a drone to perform autonomous obstacle avoidance in continuous action space using only the image data. The algorithm is trained and tested in a simulation environment built by Airsim. The results show that our algorithm enables the UAV to avoid obstacles in the training environment only by inputting the depth map. Moreover, it also has a higher obstacle avoidance rate in the reconfigured environment without retraining.

scholarly journals Collision-free path planning for welding manipulator via hybrid algorithm of deep reinforcement learning and inverse kinematics

2021 ◽  
Author(s):  
Jie Zhong ◽  
Tao Wang ◽  
Lianglun Cheng
Keyword(s):  
Reinforcement Learning ◽  
Path Planning ◽  
Free Path ◽  
Inverse Kinematics ◽  
Multiple Dimensions ◽  
Continuous State ◽  
Planning Algorithm ◽  
Convergence Performance ◽  
Path Planner ◽  
Action Spaces

AbstractIn actual welding scenarios, an effective path planner is needed to find a collision-free path in the configuration space for the welding manipulator with obstacles around. However, as a state-of-the-art method, the sampling-based planner only satisfies the probability completeness and its computational complexity is sensitive with state dimension. In this paper, we propose a path planner for welding manipulators based on deep reinforcement learning for solving path planning problems in high-dimensional continuous state and action spaces. Compared with the sampling-based method, it is more robust and is less sensitive with state dimension. In detail, to improve the learning efficiency, we introduce the inverse kinematics module to provide prior knowledge while a gain module is also designed to avoid the local optimal policy, we integrate them into the training algorithm. To evaluate our proposed planning algorithm in multiple dimensions, we conducted multiple sets of path planning experiments for welding manipulators. The results show that our method not only improves the convergence performance but also is superior in terms of optimality and robustness of planning compared with most other planning algorithms.

Adaptive co-construction of state and action spaces in reinforcement learning

2011 ◽  
Vol 16 (1) ◽  
pp. 48-52 ◽  
Author(s):  
Masato Nagayoshi ◽  
Hajime Murao ◽  
Hisashi Tamaki
Keyword(s):  
Reinforcement Learning ◽  
Action Spaces

Preceding vehicle following algorithm with human driving characteristics

2021 ◽  
pp. 095440702098154
Author(s):  
Feng Pan ◽  
Hong Bao
Keyword(s):  
Reinforcement Learning ◽  
Weight Vector ◽  
Gradient Algorithm ◽  
Inner Product ◽  
Inverse Reinforcement Learning ◽  
Reward Function ◽  
Human Driver ◽  
Policy Gradient ◽  
Preceding Vehicle ◽  
Action Spaces

This paper proposes a new approach of using reinforcement learning (RL) to train an agent to perform the task of vehicle following with human driving characteristics. We refer to the ideal of inverse reinforcement learning to design the reward function of the RL model. The factors that need to be weighed in vehicle following were vectorized into reward vectors, and the reward function was defined as the inner product of the reward vector and weights. Driving data of human drivers was collected and analyzed to obtain the true reward function. The RL model was trained with the deterministic policy gradient algorithm because the state and action spaces are continuous. We adjusted the weight vector of the reward function so that the value vector of the RL model could continuously approach that of a human driver. After dozens of rounds of training, we selected the policy with the nearest value vector to that of a human driver and tested it in the PanoSim simulation environment. The results showed the desired performance for the task of an agent following the preceding vehicle safely and smoothly.

scholarly journals What Can You Do with a Rock? Affordance Extraction via Word Embeddings

2017 ◽  
Author(s):  
Nancy Fulda ◽  
Daniel Ricks ◽  
Ben Murdoch ◽  
David Wingate
Keyword(s):  
Reinforcement Learning ◽  
Computational Complexity ◽  
Linear Algebra ◽  
Autonomous Agents ◽  
Common Knowledge ◽  
Search Space ◽  
Word Embeddings ◽  
Knowledge Database ◽  
Learning Agent ◽  
Action Spaces

Autonomous agents must often detect affordances: the set of behaviors enabled by a situation. Affordance extraction is particularly helpful in domains with large action spaces, allowing the agent to prune its search space by avoiding futile behaviors. This paper presents a method for affordance extraction via word embeddings trained on a tagged Wikipedia corpus. The resulting word vectors are treated as a common knowledge database which can be queried using linear algebra. We apply this method to a reinforcement learning agent in a text-only environment and show that affordance-based action selection improves performance in most cases. Our method increases the computational complexity of each learning step but significantly reduces the total number of steps needed. In addition, the agent's action selections begin to resemble those a human would choose.

scholarly journals DDPG Agent to Swing Up and Balance Cart- Pole System

2021 ◽  
pp. 102-116
Author(s):  
Buvanesh Pandian V
Keyword(s):  
Reinforcement Learning ◽  
Supervised Learning ◽  
Real World ◽  
Learning Algorithm ◽  
Current Approach ◽  
Control Problems ◽  
Mathematical Framework ◽  
Test Environment ◽  
Continuous Action ◽  
Action Spaces

Reinforcement learning is a mathematical framework for agents to interact intelligently with their environment. Unlike supervised learning, where a system learns with the help of labeled data, reinforcement learning agents learn how to act by trial and error only receiving a reward signal from their environments. A field where reinforcement learning has been prominently successful is robotics [3]. However, real-world control problems are also particularly challenging because of the noise and high- dimensionality of input data (e.g., visual input). In recent years, in the field of supervised learning, deep neural networks have been successfully used to extract meaning from this kind of data. Building on these advances, deep reinforcement learning was used to solve complex problems like Atari games and Go. Mnih et al. [1] built a system with fixed hyper parameters able to learn to play 49 different Atari games only from raw pixel inputs. However, in order to apply the same methods to real-world control problems, deep reinforcement learning has to be able to deal with continuous action spaces. Discretizing continuous action spaces would scale poorly, since the number of discrete actions grows exponentially with the dimensionality of the action. Furthermore, having a parametrized policy can be advantageous because it can generalize in the action space. Therefore with this thesis we study state-of-the-art deep reinforcement learning algorithm, Deep Deterministic Policy Gradients. We provide a theoretical comparison to other popular methods, an evaluation of its performance, identify its limitations and investigate future directions of research. The remainder of the thesis is organized as follows. We start by introducing the field of interest, machine learning, focusing our attention of deep learning and reinforcement learning. We continue by describing in details the two main algorithms, core of this study, namely Deep Q-Network (DQN) and Deep Deterministic Policy Gradients (DDPG). We then provide implementatory details of DDPG and our test environment, followed by a description of benchmark test cases. Finally, we discuss the results of our evaluation, identifying limitations of the current approach and proposing future avenues of research.

Sign in / Sign up

Export Citation Format

Share Document