380 citations · 725 across the 16 of their papers we have counts for
19 papers
PopGen: Generating Semantically Diverse Populations for Zero-Shot Coordination
Paul Teiletche, Kanghyun Ryu, Kyungjoon Park +3
In multi-agent reinforcement learning, exposing a cooperator to partners with diverse strategies during training is key to better collaboration at test time. However, existing meth…
HuGo: LLMs as Whole-Body Policy Code Designers for Humanoid Loco-Manipulation
Seoyeon Choi, Shizhao Ye, Nicholas Bui +5
For humanoids to be useful in everyday environments, they must perform a wide range of tasks that couple locomotion and manipulation. Existing approaches commonly acquire a loco-ma…
What Matters for Simulation to Online Reinforcement Learning on Real Robots
Yarden As, Dhruva Tirumala, René Zurbrügg +4
We investigate what specific design choices enable successful online reinforcement learning (RL) on physical robots. Across 100 real-world training runs on three distinct robotic p…
A KL-regularization Framework for Learning to Plan with Adaptive Priors
Álvaro Serra-Gomez, Daniel Jarne Ornia, Dhruva Tirumala +1
Effective exploration remains a central challenge in model-based reinforcement learning (MBRL), particularly in high-dimensional continuous control tasks where sample efficiency is…
Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning
Dhruva Tirumala, Markus Wulfmeier, Ben Moran +13
We apply multi-agent deep reinforcement learning (RL) to train end-to-end robot soccer policies with fully onboard computation and sensing via egocentric RGB vision. This setting r…
Replay across Experiments: A Natural Extension of Off-Policy RL
Dhruva Tirumala, Thomas Lampe, Jose Enrique Chen +9
Replaying data is a principal mechanism underlying the stability and data efficiency of off-policy reinforcement learning (RL). We present an effective yet simple framework to exte…
Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
Tuomas Haarnoja, Ben Moran, Guy Lever +25
We investigate whether Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot that can be compo…
SkillS: Adaptive Skill Sequencing for Efficient Temporally-Extended Exploration
Giulia Vezzani, Dhruva Tirumala, Markus Wulfmeier +13
The ability to effectively reuse prior knowledge is a key requirement when building general and flexible Reinforcement Learning (RL) agents. Skill reuse is one of the most common a…
MO2: Model-Based Offline Options
Sasha Salter, Markus Wulfmeier, Dhruva Tirumala +4
The ability to discover useful behaviours from past experience and transfer them to new tasks is considered a core component of natural embodied intelligence. Inspired by neuroscie…
Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies
Dushyant Rao, Fereshteh Sadeghi, Leonard Hasenclever +8
For robots operating in the real world, it is desirable to learn reusable behaviours that can effectively be transferred and adapted to numerous tasks and scenarios. We propose an…
Pick Your Battles: Interaction Graphs as Population-Level Objectives for Strategic Diversity
Marta Garnelo, Wojciech Marian Czarnecki, Siqi Liu +5
Strategic diversity is often essential in games: in multi-player games, for example, evaluating a player against a diverse set of strategies will yield a more accurate estimate of…
Behavior Priors for Efficient Reinforcement Learning
Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh +8
As we deploy reinforcement learning agents to solve increasingly challenging problems, methods that allow us to inject prior knowledge about the structure of the world and effectiv…
Data-efficient Hindsight Off-policy Option Learning
Markus Wulfmeier, Dushyant Rao, Roland Hafner +8
We introduce Hindsight Off-policy Options (HO2), a data-efficient option learning algorithm. Given any trajectory, HO2 infers likely option choices and backpropagates through the d…
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
H. Francis Song, Abbas Abdolmaleki, Jost Tobias Springenberg +11
Some of the most successful applications of deep reinforcement learning to challenging domains in discrete and continuous control have used policy gradient methods in the on-policy…
Information asymmetry in KL-regularized RL
Alexandre Galashov, Siddhant M. Jayakumar, Leonard Hasenclever +7
Many real world tasks exhibit rich structure that is repeated across different parts of the state space or in time. In this work we study the possibility of leveraging such repeate…
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
Dhruva Tirumala, Hyeonwoo Noh, Alexandre Galashov +6
As reinforcement learning agents are tasked with solving more challenging and diverse tasks, the ability to incorporate prior knowledge into the learning system and to exploit reus…
Hierarchical visuomotor control of humanoids
Josh Merel, Arun Ahuja, Vu Pham +5
We aim to build complex humanoid agents that integrate perception, motor control, and memory. In this work, we partly factor this problem into low-level motor control from proprioc…
Flexible Support for Fast Parallel Commutative Updates
Vignesh Balaji, Dhruva Tirumala, Brandon Lucia
Privatizing data is a useful strategy for increasing parallelism in a shared memory multithreaded program. Independent cores can compute independently on duplicates of shared data,…
Learning to reinforcement learn
Jane X Wang, Zeb Kurth-Nelson, Dhruva Tirumala +6
In recent years deep reinforcement learning (RL) systems have attained superhuman performance in a number of challenging task domains. However, a major limitation of such applicati…