Pseudorehearsal in actor-critic agents

04/17/2017
by   Marochko Vladimir, et al.
0

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 balancing task and compare different pseudorehearsal approaches. We expect that pseudorehearsal assists learning even in such very simple problems, given proper initialization of the rehearsal parameters.

READ FULL TEXT

page 1

page 2

page 3

research
12/20/2017

Pseudorehearsal in actor-critic agents with neural network function approximation

Catastrophic forgetting has a significant negative impact in reinforceme...
research
05/07/2021

Context-Based Soft Actor Critic for Environments with Non-stationary Dynamics

The performance of deep reinforcement learning methods prone to degenera...
research
08/19/2022

Unified Policy Optimization for Continuous-action Reinforcement Learning in Non-stationary Tasks and Games

This paper addresses policy learning in non-stationary environments and ...
research
10/09/2019

Integrating Behavior Cloning and Reinforcement Learning for Improved Performance in Sparse Reward Environments

This paper investigates how to efficiently transition and update policie...
research
12/18/2022

Neural Coreference Resolution based on Reinforcement Learning

The target of a coreference resolution system is to cluster all mentions...
research
07/05/2022

Ask-AC: An Initiative Advisor-in-the-Loop Actor-Critic Framework

Despite the promising results achieved, state-of-the-art interactive rei...
research
08/19/2023

PACE: Improving Prompt with Actor-Critic Editing for Large Language Model

Large language models (LLMs) have showcased remarkable potential across ...

Please sign up or login with your details

Forgot password? Click here to reset