187 citations · 482 across the 18 of their papers we have counts for
16 papers · 1 filter
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play
Daniel Bairamian, Philippe Marcotte, Joshua Romoff +2
Recent advances in Competitive Self-Play (CSP) have achieved, or even surpassed, human level performance in complex game environments such as Dota 2 and StarCraft II using Distribu…
Improving Intrinsic Exploration by Creating Stationary Objectives
Roger Creus Castanyer, Joshua Romoff, Glen Berseth
Exploration bonuses in reinforcement learning guide long-horizon exploration by defining custom intrinsic objectives. Several exploration objectives like count-based bonuses, pseud…
Learning Computational Efficient Bots with Costly Features
Anthony Kobanda, Valliappan C. A., Joshua Romoff +1
Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes. However, a challenge that often arises is the trade-off…
Graph augmented Deep Reinforcement Learning in the GameRLand3D environment
Edward Beeching, Maxim Peter, Philippe Marcotte +4
We address planning and navigation in challenging 3D video games featuring maps with disconnected regions reachable by agents using special actions. In this setting, classical symb…
Direct Behavior Specification via Constrained Reinforcement Learning
Julien Roy, Roger Girgis, Joshua Romoff +2
The standard formulation of Reinforcement Learning lacks a practical way of specifying what are admissible and forbidden behaviors. Most often, practitioners go about the task of b…
Deep Reinforcement Learning for Navigation in AAA Video Games
Eloi Alonso, Maxim Peter, David Goumard +1
In video games, non-player characters (NPCs) are used to enhance the players' experience in a variety of ways, e.g., as enemies, allies, or innocent bystanders. A crucial component…
TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
Joshua Romoff, Peter Henderson, David Kanaa +4
We investigate whether Jacobi preconditioning, accounting for the bootstrap term in temporal difference (TD) learning, can help boost performance of adaptive optimizers. Our method…
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
Mahmoud Assran, Joshua Romoff, Nicolas Ballas +2
Multi-simulator training has contributed to the recent success of Deep Reinforcement Learning by stabilizing learning and allowing for higher training throughputs. We propose Gossi…
Separating value functions across time-scales
Joshua Romoff, Peter Henderson, Ahmed Touati +3
In many finite horizon episodic reinforcement learning (RL) settings, it is desirable to optimize for the undiscounted return - in settings like Atari, for instance, the goal is to…
Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
Peter Henderson, Joshua Romoff, Joelle Pineau
Recent analyses of certain gradient descent optimization methods have shown that performance can degrade in some settings - such as with stochasticity or implicit momentum. In deep…
TarMAC: Targeted Multi-Agent Communication
Abhishek Das, Théophile Gervet, Joshua Romoff +4
We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing…
Randomized Value Functions via Multiplicative Normalizing Flows
Ahmed Touati, Harsh Satija, Joshua Romoff +2
Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike t…
Reward Estimation for Variance Reduction in Deep Reinforcement Learning
Joshua Romoff, Peter Henderson, Alexandre Piché +2
Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high varia…
Hybrid Reward Architecture for Reinforcement Learning
Harm van Seijen, Mehdi Fatemi, Joshua Romoff +3
One of the main challenges in reinforcement learning (RL) is generalisation. In typical deep RL methods this is achieved by approximating the optimal value function with a low-dime…
Multi-Advisor Reinforcement Learning
Romain Laroche, Mehdi Fatemi, Joshua Romoff +1
We consider tackling a single-agent RL problem by distributing it to learners. These learners, called advisors, endeavour to solve the problem from a different focus. Their adv…
Separation of Concerns in Reinforcement Learning
Harm van Seijen, Mehdi Fatemi, Joshua Romoff +1
In this paper, we propose a framework for solving a single-agent task by using multiple agents, each focusing on different aspects of the task. This approach has two main advantage…