Search Results for author:
Found 17 papers, 9 papers with code
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play
In this paper, we propose the Minimax Exploiter, a game theoretic approach to exploiting Main Agents that leverages knowledge of its opponents, leading to significant increases in data efficiency.
Improving Intrinsic Exploration by Creating Stationary Objectives
Several exploration objectives like count-based bonuses, pseudo-counts, and state-entropy maximization are non-stationary and hence are difficult to optimize for the agent.
Learning Computational Efficient Bots with Costly Features
Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes.
Graph augmented Deep Reinforcement Learning in the GameRLand3D environment
We address planning and navigation in challenging 3D video games featuring maps with disconnected regions reachable by agents using special actions.
Direct Behavior Specification via Constrained Reinforcement Learning
The standard formulation of Reinforcement Learning lacks a practical way of specifying what are admissible and forbidden behaviors.
Deep Reinforcement Learning for Navigation in AAA Video Games
We test our approach on complex 3D environments in the Unity game engine that are notably an order of magnitude larger than maps typically used in the Deep RL literature.
TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
We investigate whether Jacobi preconditioning, accounting for the bootstrap term in temporal difference (TD) learning, can help boost performance of adaptive optimizers.
Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning
Accurate reporting of energy and carbon usage is essential for understanding the potential climate impacts of machine learning research.
Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning
We show that we can run several loosely coupled GALA agents in parallel on a single GPU and achieve significantly higher hardware utilization and frame-rates than vanilla A2C at comparable power draws.
Separating value functions across time-scales
In settings where this bias is unacceptable - where the system must optimize for longer horizons at higher discounts - the target of the value function approximator may increase in variance leading to difficulties in learning.
TarMAC: Targeted Multi-Agent Communication
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 cooperative tasks in partially-observable environments.
Where Did My Optimum Go?: An Empirical Analysis of Gradient Descent Optimization in Policy Gradient Methods
We find that adaptive optimizers have a narrow window of effective learning rates, diverging in other cases, and that the effectiveness of momentum varies depending on the properties of the environment.
Randomized Value Functions via Multiplicative Normalizing Flows
In particular, we augment DQN and DDPG with multiplicative normalizing flows in order to track a rich approximate posterior distribution over the parameters of the value function.
Reward Estimation for Variance Reduction in Deep Reinforcement Learning
However, introduction of corrupt or stochastic rewards can yield high variance in learning.
Hybrid Reward Architecture for Reinforcement Learning
One of the main challenges in reinforcement learning (RL) is generalisation.
Multi-Advisor Reinforcement Learning
We consider tackling a single-agent RL problem by distributing it to $n$ learners.
Separation of Concerns in Reinforcement Learning
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.
