DeepAI
Log In Sign Up

Improved Memories Learning

08/24/2020
by   Francesco Varoli, et al.
0

We propose Improved Memories Learning (IMeL), a novel algorithm that turns reinforcement learning (RL) into a supervised learning (SL) problem and delimits the role of neural networks (NN) to interpolation. IMeL consists of two components. The first is a reservoir of experiences. Each experience is updated based on a non-parametric procedural improvement of the policy, computed as a bounded one-sample Monte Carlo estimate. The second is a NN regressor, which receives as input improved experiences from the reservoir (context points) and computes the policy by interpolation. The NN learns to measure the similarity between states in order to compute long-term forecasts by averaging experiences, rather than by encoding the problem structure in the NN parameters. We present preliminary results and propose IMeL as a baseline method for assessing the merits of more complex models and inductive biases.

READ FULL TEXT

page 1

page 2

page 3

page 4

01/26/2023

Which Experiences Are Influential for Your Agent? Policy Iteration with Turn-over Dropout

In reinforcement learning (RL) with experience replay, experiences store...
07/01/2021

MHER: Model-based Hindsight Experience Replay

Solving multi-goal reinforcement learning (RL) problems with sparse rewa...
10/09/2021

Theoretically Principled Deep RL Acceleration via Nearest Neighbor Function Approximation

Recently, deep reinforcement learning (RL) has achieved remarkable empir...
05/29/2017

Role Playing Learning for Socially Concomitant Mobile Robot Navigation

In this paper, we present the Role Playing Learning (RPL) scheme for a m...
02/17/2022

Retrieval-Augmented Reinforcement Learning

Most deep reinforcement learning (RL) algorithms distill experience into...
07/07/2022

Sampling from Pre-Images to Learn Heuristic Functions for Classical Planning

We introduce a new algorithm, Regression based Supervised Learning (RSL)...