521 citations · 1.2k across the 41 of their papers we have counts for
22 papers · 1 filter
Value from Observations: Towards Large-Scale Imitation Learning via Self-Improvement
Michael Bloesch, Markus Wulfmeier, Philemon Brakel +8
Imitation Learning from Observation (IfO) offers a powerful way to learn behaviors at large-scale: Unlike behavior cloning or offline reinforcement learning, IfO can leverage actio…
Learning from negative feedback, or positive feedback or both
Abbas Abdolmaleki, Bilal Piot, Bobak Shahriari +9
Existing preference optimization methods often assume scenarios where paired preference feedback (preferred/positive vs. dis-preferred/negative examples) is available. This require…
Offline Actor-Critic Reinforcement Learning Scales to Large Models
Jost Tobias Springenberg, Abbas Abdolmaleki, Jingwei Zhang +9
We show that offline actor-critic reinforcement learning can scale to large models - such as transformers - and follows similar scaling laws as supervised learning. We find that of…
Policy composition in reinforcement learning via multi-objective policy optimization
Shruti Mishra, Ankit Anand, Jordan Hoffmann +4
We enable reinforcement learning agents to learn successful behavior policies by utilizing relevant pre-existing teacher policies. The teacher policies are introduced as objectives…
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…
Revisiting Gaussian mixture critics in off-policy reinforcement learning: a sample-based approach
Bobak Shahriari, Abbas Abdolmaleki, Arunkumar Byravan +6
Actor-critic algorithms that make use of distributional policy evaluation have frequently been shown to outperform their non-distributional counterparts on many challenging control…
On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning
Abbas Abdolmaleki, Sandy H. Huang, Giulia Vezzani +11
Many advances that have improved the robustness and efficiency of deep reinforcement learning (RL) algorithms can, in one way or another, be understood as introducing additional ob…
Decoupled Exploration and Exploitation Policies for Sample-Efficient Reinforcement Learning
William F. Whitney, Michael Bloesch, Jost Tobias Springenberg +3
Despite the close connection between exploration and sample efficiency, most state of the art reinforcement learning algorithms include no considerations for exploration beyond max…
Local Search for Policy Iteration in Continuous Control
Jost Tobias Springenberg, Nicolas Heess, Daniel Mankowitz +10
We present an algorithm for local, regularized, policy improvement in reinforcement learning (RL) that allows us to formulate model-based and model-free variants in a single framew…
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…
Acme: A Research Framework for Distributed Reinforcement Learning
Matthew W. Hoffman, Bobak Shahriari, John Aslanides +36
Deep reinforcement learning (RL) has led to many recent and groundbreaking advances. However, these advances have often come at the cost of both increased scale in the underlying a…
A Distributional View on Multi-Objective Policy Optimization
Abbas Abdolmaleki, Sandy H. Huang, Leonard Hasenclever +7
Many real-world problems require trading off multiple competing objectives. However, these objectives are often in different units and/or scales, which can make it challenging for…
Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning
Noah Y. Siegel, Jost Tobias Springenberg, Felix Berkenkamp +6
Off-policy reinforcement learning algorithms promise to be applicable in settings where only a fixed data-set (batch) of environment interactions is available and no new experience…
Continuous-Discrete Reinforcement Learning for Hybrid Control in Robotics
Michael Neunert, Abbas Abdolmaleki, Markus Wulfmeier +7
Many real-world control problems involve both discrete decision variables - such as the choice of control modes, gear switching or digital outputs - as well as continuous decision…
Quinoa: a Q-function You Infer Normalized Over Actions
Jonas Degrave, Abbas Abdolmaleki, Jost Tobias Springenberg +2
We present an algorithm for learning an approximate action-value soft Q-function in the relative entropy regularised reinforcement learning setting, for which an optimal improved p…
Augmenting learning using symmetry in a biologically-inspired domain
Shruti Mishra, Abbas Abdolmaleki, Arthur Guez +2
Invariances to translation, rotation and other spatial transformations are a hallmark of the laws of motion, and have widespread use in the natural sciences to reduce the dimension…
Compositional Transfer in Hierarchical Reinforcement Learning
Markus Wulfmeier, Abbas Abdolmaleki, Roland Hafner +7
The successful application of general reinforcement learning algorithms to real-world robotics applications is often limited by their high data requirements. We introduce Regulariz…
Robust Reinforcement Learning for Continuous Control with Model Misspecification
Daniel J. Mankowitz, Nir Levine, Rae Jeong +7
We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcem…
Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup
Devin Schwab, Tobias Springenberg, Murilo F. Martins +7
We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary…
Relative Entropy Regularized Policy Iteration
Abbas Abdolmaleki, Jost Tobias Springenberg, Jonas Degrave +5
We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value…
Maximum a Posteriori Policy Optimisation
Abbas Abdolmaleki, Jost Tobias Springenberg, Yuval Tassa +3
We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show tha…
Model-Free Trajectory-based Policy Optimization with Monotonic Improvement
Riad Akrour, Abbas Abdolmaleki, Hany Abdulsamad +2
Many of the recent trajectory optimization algorithms alternate between linear approximation of the system dynamics around the mean trajectory and conservative policy update. One w…