Search Results for author:
Found 30 papers, 5 papers with code
CoMic: Co-Training and Mimicry for Reusable Skills
Finally we show that it is possible to interleave the motion capture tracking with training on complementary tasks, enriching the resulting skill space, and enabling the reuse of skills not well covered by the motion capture data such as getting up from the ground or catching a ball.
A distributional view on multi objective policy optimization
Many real-world problems require trading off multiple competing objectives.
Replay across Experiments: A Natural Extension of Off-Policy RL
Replaying data is a principal mechanism underlying the stability and data efficiency of off-policy reinforcement learning (RL).
Towards A Unified Agent with Foundation Models
Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others.
Language to Rewards for Robotic Skill Synthesis
However, since low-level robot actions are hardware-dependent and underrepresented in LLM training corpora, existing efforts in applying LLMs to robotics have largely treated LLMs as semantic planners or relied on human-engineered control primitives to interface with the robot.
A Generalist Dynamics Model for Control
We investigate the use of transformer sequence models as dynamics models (TDMs) for control.
Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning
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 composed into complex behavioral strategies in dynamic environments.
Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains
We conduct a set of experiments in the RGB-stacking environment, showing that planning with the learned skills and the associated model can enable zero-shot generalization to new tasks, and can further speed up training of policies via reinforcement learning.
NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields
A simulation is then created using the rendering engine in a physics simulator which computes contact dynamics from the static scene geometry (estimated from the NeRF volume density) and the dynamic objects' geometry and physical properties (assumed known).
Imitate and Repurpose: Learning Reusable Robot Movement Skills From Human and Animal Behaviors
We investigate the use of prior knowledge of human and animal movement to learn reusable locomotion skills for real legged robots.
Learning Transferable Motor Skills with Hierarchical Latent Mixture Policies
We demonstrate in manipulation domains that the method can effectively cluster offline data into distinct, executable behaviours, while retaining the flexibility of a continuous latent variable model.
Learning Coordinated Terrain-Adaptive Locomotion by Imitating a Centroidal Dynamics Planner
Imitation learning circumvents this problem and has been used with motion capture data to extract quadruped gaits for flat terrains.
Evaluating model-based planning and planner amortization for continuous control
There is a widespread intuition that model-based control methods should be able to surpass the data efficiency of model-free approaches.
Learning Dynamics Models for Model Predictive Agents
This paper sets out to disambiguate the role of different design choices for learning dynamics models, by comparing their performance to planning with a ground-truth model -- the simulator.
From Motor Control to Team Play in Simulated Humanoid Football
In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements such as running and turning; they then acquire mid-level football skills such as dribbling and shooting; finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds, and coordinated goal-directed behaviour as a team at the timescale of tens of seconds.
Divide-and-Conquer Monte Carlo Tree Search
are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed.
Behavior Priors for Efficient Reinforcement Learning
In this work we consider how information and architectural constraints can be combined with ideas from the probabilistic modeling literature to learn behavior priors that capture the common movement and interaction patterns that are shared across a set of related tasks or contexts.
Importance Weighted Policy Learning and Adaptation
The ability to exploit prior experience to solve novel problems rapidly is a hallmark of biological learning systems and of great practical importance for artificial ones.
A Distributional View on Multi-Objective Policy Optimization
Many real-world problems require trading off multiple competing objectives.
Divide-and-Conquer Monte Carlo Tree Search For Goal-Directed Planning
are constrained by an implicit sequential planning assumption: The order in which a plan is constructed is the same in which it is executed.
Catch & Carry: Reusable Neural Controllers for Vision-Guided Whole-Body Tasks
We address the longstanding challenge of producing flexible, realistic humanoid character controllers that can perform diverse whole-body tasks involving object interactions.
Meta reinforcement learning as task inference
This includes proposals to learn the learning algorithm itself, an idea also known as meta learning.
Information asymmetry in KL-regularized RL
In this work we study the possibility of leveraging such repeated structure to speed up and regularize learning.
Exploiting Hierarchy for Learning and Transfer in KL-regularized RL
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 reusable structure in solution space is likely to become increasingly important.
Neural probabilistic motor primitives for humanoid control
We focus on the problem of learning a single motor module that can flexibly express a range of behaviors for the control of high-dimensional physically simulated humanoids.
Mix & Match - Agent Curricula for Reinforcement Learning
We introduce Mix and match (M&M) – a training framework designed to facilitate rapid and effective learning in RL agents that would be too slow or too challenging to train otherwise. The key innovation is a procedure that allows us to automatically form a curriculum over agents.
Mix&Match - Agent Curricula for Reinforcement Learning
(2) We further show that M&M can be used successfully to progress through a curriculum of architectural variants defining an agents internal state.
Sylvester Normalizing Flows for Variational Inference
Variational inference relies on flexible approximate posterior distributions.
Relativistic Monte Carlo
Based on this, we develop relativistic stochastic gradient descent by taking the zero-temperature limit of relativistic stochastic gradient Hamiltonian Monte Carlo.
Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server
The posterior server allows scalable and robust Bayesian learning in cases where a data set is stored in a distributed manner across a cluster, with each compute node containing a disjoint subset of data.
