Figure 1 - uploaded by Vladimir Andreevich Marochko
Content may be subject to copyright.
Download
View publication
Scheme of information flows in actor-critic agent 

Scheme of information flows in actor-critic agent 

Source publication
Figure 1: Scheme of information flows in actor-critic agent 
Figure 2: double-pole cart 
Figure 3: Agent successfully learned to high efficiency, but than CF...
Figure 4: One of examples which shows how tendency graph can make...
+15 Figure 5: Tendency graph for difference between agent with...
Pseudorehearsal in actor-critic agents
Thesis
Full-text available
  • May 2017
Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can increase performance of an actor-critic agent with neural-network based policy selection and function approximation in a pole balan...
Cite
Download full-text

Similar publications

View
Fig. 1. Double-pole cart
Fig. 2. Tendency graph for the difference between the agent with PR...
Fig. 5. Batch-backpropagation based PR example
Fig. 7. Comparing batch backpropagation PR and FR PR
+1 Fig. 9. Agents performance with learning-rate correction PR
Pseudorehearsal in Actor-Critic Agents with Neural Network Function Approximation
Preprint
Full-text available
  • May 2018
Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network function approximation. We tested agent in a pole balancing task and compared different pseudorehearsal approaches. We have found tha...
View
Fig. 1. Double-pole cart 
Fig. 2. Tendency graph for the difference between the agent with PR...
Fig. 5. Batch-backpropagation based PR example 
Fig. 6. Comparing batch-backpropagation PR and FR PR by tendency graph. 
+2 Fig. 7. Comparing batch backpropagation PR and FR PR
Pseudorehearsal in actor-critic agents with neural network function approximation
Preprint
Full-text available
  • Jan 2018
Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network function approximation. We tested agent in a pole balancing task and compared different pseudorehearsal approaches. We have found tha...
View

Citations

... Actor-critics can also learn an explicitly stochastic policy which is very useful in continuous learning problems." [8]. The actor receives the current state from the environment and performs an action depending on its policy. ...
Design of a Neural Controller Using Reinforcement Learning to Control a Rotational Inverted Pendulum
Conference Paper
  • Dec 2020
Artificial intelligence (AI) has an increasing influence in the manufacturing and processing industries. An increasingly interesting area of application is the design of controllers for technical systems through reinforcement learning. This allows the design of a controller with reduced effort for human experts, which is normally involved in the design process, for example by eliminating the determination of suitable controller parameters. In this paper a neural controller for a rotational inverted pendulum is developed by using artificial neural networks in combination with reinforcement learning. The rotational inverted pendulum is a classic example of a nonlinear and unstable system and has been little covered in previous publications on this subject. Furthermore, the behaviour of the neural controller is compared with a conventional controller when swinging up and balancing a rotational inverted pendulum.
View