11 papers
EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
Thomas Evers, Cristian Meo, Wendelin Bohmer +2
We introduce EfficientTDMPC, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms. Central to this family is…
AlphaExploitem: Going Beyond the Nash Equilibrium in Poker by Learning to Exploit Suboptimal Play
Vlad Murgoci, Matthijs Spaan, Yaniv Oren
Poker is an imperfect information game that has served as a long-standing benchmark for decision-making under uncertainty. To maximize utility beyond the Nash equilibrium, an agent…
Particle Monte Carlo Tree Search
Yaniv Oren, Viliam Vadocz, Joery A. de Vries +3
Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement and action selection in Reinforcement Learning. Due to its sequential and deterministic nature, prin…
VariBASed: Variational Bayes-Adaptive Sequential Monte-Carlo Planning for Deep Reinforcement Learning
Joery A. de Vries, Jinke He, Yaniv Oren +3
Optimally trading-off exploration and exploitation is the holy grail of reinforcement learning as it promises maximal data-efficiency for solving any task. Bayes-optimal agents ach…
Twice Sequential Monte Carlo for Tree Search
Yaniv Oren, Joery A. de Vries, Pascal R. van der Vaart +2
Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alt…
RecBayes: Recurrent Bayesian Ad Hoc Teamwork in Large Partially Observable Domains
João G. Ribeiro, Yaniv Oren, Alberto Sardinha +2
This paper proposes RecBayes, a novel approach for ad hoc teamwork under partial observability, a setting where agents are deployed on-the-fly to environments where pre-existing te…
Universal Value-Function Uncertainties
Moritz A. Zanger, Max Weltevrede, Yaniv Oren +4
Estimating epistemic uncertainty in value functions is a crucial challenge for many aspects of reinforcement learning (RL), including efficient exploration, safe decision-making, a…
Bridging the Performance Gap Between Target-Free and Target-Based Reinforcement Learning
Théo Vincent, Yogesh Tripathi, Tim Faust +5
The use of target networks in deep reinforcement learning is a widely popular solution to mitigate the brittleness of semi-gradient approaches and stabilize learning. However, targ…
Trust-Region Twisted Policy Improvement
Joery A. de Vries, Jinke He, Yaniv Oren +1
Monte-Carlo tree search (MCTS) has driven many recent breakthroughs in deep reinforcement learning (RL). However, scaling MCTS to parallel compute has proven challenging in practic…
Value Improved Actor Critic Algorithms
Yaniv Oren, Moritz A. Zanger, Pascal R. van der Vaart +3
To learn approximately optimal acting policies for decision problems, modern Actor Critic algorithms rely on deep Neural Networks (DNNs) to parameterize the acting policy and greed…
Epistemic Monte Carlo Tree Search
Yaniv Oren, Viliam Vadocz, Matthijs T. J. Spaan +1
The AlphaZero/MuZero (A/MZ) family of algorithms has achieved remarkable success across various challenging domains by integrating Monte Carlo Tree Search (MCTS) with learned model…