Search Results for author:
Found 17 papers, 11 papers with code
H-GAP: Humanoid Control with a Generalist Planner
However, the extensive collection of human motion-captured data and the derived datasets of humanoid trajectories, such as MoCapAct, paves the way to tackle these challenges.
Deep Generative Models for Decision-Making and Control
Deep model-based reinforcement learning methods offer a conceptually simple approach to the decision-making and control problem: use learning for the purpose of estimating an approximate dynamics model, and offload the rest of the work to classical trajectory optimization.
Training Diffusion Models with Reinforcement Learning
However, most use cases of diffusion models are not concerned with likelihoods, but instead with downstream objectives such as human-perceived image quality or drug effectiveness.
IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies
In this paper, we reinterpret IQL as an actor-critic method by generalizing the critic objective and connecting it to a behavior-regularized implicit actor.
Efficient Planning in a Compact Latent Action Space
Planning-based reinforcement learning has shown strong performance in tasks in discrete and low-dimensional continuous action spaces.
Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control
Learned models and policies can generalize effectively when evaluated within the distribution of the training data, but can produce unpredictable and erroneous outputs on out-of-distribution inputs.
Planning with Diffusion for Flexible Behavior Synthesis
Model-based reinforcement learning methods often use learning only for the purpose of estimating an approximate dynamics model, offloading the rest of the decision-making work to classical trajectory optimizers.
Reinforcement Learning as One Big Sequence Modeling Problem
However, we can also view RL as a sequence modeling problem, with the goal being to predict a sequence of actions that leads to a sequence of high rewards.
Offline Reinforcement Learning as One Big Sequence Modeling Problem
Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time.
Gamma-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction
We introduce the gamma-model, a predictive model of environment dynamics with an infinite, probabilistic horizon.
Generative Temporal Difference Learning for Infinite-Horizon Prediction
We introduce the $\gamma$-model, a predictive model of environment dynamics with an infinite probabilistic horizon.
Entity Abstraction in Visual Model-Based Reinforcement Learning
This paper tests the hypothesis that modeling a scene in terms of entities and their local interactions, as opposed to modeling the scene globally, provides a significant benefit in generalizing to physical tasks in a combinatorial space the learner has not encountered before.
When to Trust Your Model: Model-Based Policy Optimization
Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data.
Model-based Reinforcement Learning
reinforcement-learning
+1
Reasoning About Physical Interactions with Object-Centric Models
Object-based factorizations provide a useful level of abstraction for interacting with the world.
Reasoning About Physical Interactions with Object-Oriented Prediction and Planning
Object-based factorizations provide a useful level of abstraction for interacting with the world.
Self-Supervised Intrinsic Image Decomposition
Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data.
Representation Learning for Grounded Spatial Reasoning
The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment.
