Towards a standardised performance evaluation protocol for cooperative marl
R Gorsane, O Mahjoub, RJ de Kock… - Advances in …, 2022 - proceedings.neurips.cc
Multi-agent reinforcement learning (MARL) has emerged as a useful approach to solving
decentralised decision-making problems at scale. Research in the field has been growing …
decentralised decision-making problems at scale. Research in the field has been growing …
Stock market prediction using deep reinforcement learning
AL Awad, SM Elkaffas, MW Fakhr - Applied System Innovation, 2023 - mdpi.com
Stock value prediction and trading, a captivating and complex research domain, continues to
draw heightened attention. Ensuring profitable returns in stock market investments demands …
draw heightened attention. Ensuring profitable returns in stock market investments demands …
Asymmetric DQN for partially observable reinforcement learning
Offline training in simulated partially observable environments allows reinforcement learning
methods to exploit privileged state information through a mechanism known as asymmetry …
methods to exploit privileged state information through a mechanism known as asymmetry …
Unbiased asymmetric reinforcement learning under partial observability
In partially observable reinforcement learning, offline training gives access to latent
information which is not available during online training and/or execution, such as the …
information which is not available during online training and/or execution, such as the …
Learning controlled and targeted communication with the centralized critic for the multi-agent system
Multi-agent deep reinforcement learning (MDRL) has attracted attention for solving complex
tasks. Two main challenges of MDRL are non-stationarity and partial observability from the …
tasks. Two main challenges of MDRL are non-stationarity and partial observability from the …
Formal Modelling for Multi-Robot Systems Under Uncertainty
Abstract Purpose of Review To effectively synthesise and analyse multi-robot behaviour, we
require formal task-level models which accurately capture multi-robot execution. In this …
require formal task-level models which accurately capture multi-robot execution. In this …
Factored Online Planning in Many-Agent POMDPs
In centralized multi-agent systems, often modeled as multi-agent partially observable
Markov decision processes (MPOMDPs), the action and observation spaces grow …
Markov decision processes (MPOMDPs), the action and observation spaces grow …
Leveraging Mutual Information for Asymmetric Learning under Partial Observability
Even though partial observability is prevalent in robotics, most reinforcement learning
studies avoid it due to the difficulty of learning a policy that can efficiently memorize past …
studies avoid it due to the difficulty of learning a policy that can efficiently memorize past …