1.1k citations · 5k across the 117 of their papers we have counts for
14 papers · 1 filter
Particle-Based Score Estimation for State Space Model Learning in Autonomous Driving
Angad Singh, Omar Makhlouf, Maximilian Igl +3
Multi-object state estimation is a fundamental problem for robotic applications where a robot must interact with other moving objects. Typically, other objects' relevant state feat…
Embedding Synthetic Off-Policy Experience for Autonomous Driving via Zero-Shot Curricula
Eli Bronstein, Sirish Srinivasan, Supratik Paul +4
ML-based motion planning is a promising approach to produce agents that exhibit complex behaviors, and automatically adapt to novel environments. In the context of autonomous drivi…
Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios
Yiren Lu, Justin Fu, George Tucker +9
Imitation learning (IL) is a simple and powerful way to use high-quality human driving data, which can be collected at scale, to produce human-like behavior. However, policies base…
SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning
Benjamin Ellis, Jonathan Cook, Skander Moalla +5
The availability of challenging benchmarks has played a key role in the recent progress of machine learning. In cooperative multi-agent reinforcement learning, the StarCraft Multi-…
Hypernetworks in Meta-Reinforcement Learning
Jacob Beck, Matthew Thomas Jackson, Risto Vuorio +1
Training a reinforcement learning (RL) agent on a real-world robotics task remains generally impractical due to sample inefficiency. Multi-task RL and meta-RL aim to improve sample…
Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving
Eli Bronstein, Mark Palatucci, Dominik Notz +14
We demonstrate the first large-scale application of model-based generative adversarial imitation learning (MGAIL) to the task of dense urban self-driving. We augment standard MGAIL…
Equivariant Networks for Zero-Shot Coordination
Darius Muglich, Christian Schroeder de Witt, Elise van der Pol +2
Successful coordination in Dec-POMDPs requires agents to adopt robust strategies and interpretable styles of play for their partner. A common failure mode is symmetry breaking, whe…
An Investigation of the Bias-Variance Tradeoff in Meta-Gradients
Risto Vuorio, Jacob Beck, Shimon Whiteson +2
Meta-gradients provide a general approach for optimizing the meta-parameters of reinforcement learning (RL) algorithms. Estimation of meta-gradients is central to the performance o…
Generalized Beliefs for Cooperative AI
Darius Muglich, Luisa Zintgraf, Christian Schroeder de Witt +2
Self-play is a common paradigm for constructing solutions in Markov games that can yield optimal policies in collaborative settings. However, these policies often adopt highly-spec…
Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation
Maximilian Igl, Daewoo Kim, Alex Kuefler +7
Simulation is a crucial tool for accelerating the development of autonomous vehicles. Making simulation realistic requires models of the human road users who interact with such car…
Generalization in Cooperative Multi-Agent Systems
Anuj Mahajan, Mikayel Samvelyan, Tarun Gupta +4
Collective intelligence is a fundamental trait shared by several species of living organisms. It has allowed them to thrive in the diverse environmental conditions that exist on ou…
Trust Region Bounds for Decentralized PPO Under Non-stationarity
Mingfei Sun, Sam Devlin, Jacob Beck +2
We present trust region bounds for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL), which holds even when the transition dynamics are non…
You May Not Need Ratio Clipping in PPO
Mingfei Sun, Vitaly Kurin, Guoqing Liu +4
Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. R…
In Defense of the Unitary Scalarization for Deep Multi-Task Learning
Vitaly Kurin, Alessandro De Palma, Ilya Kostrikov +2
Recent multi-task learning research argues against unitary scalarization, where training simply minimizes the sum of the task losses. Several ad-hoc multi-task optimization algorit…