
-
MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale
General-purpose robotic systems must master a large repertoire of divers...
read it
-
Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills
We consider the problem of learning useful robotic skills from previousl...
read it
-
RECON: Rapid Exploration for Open-World Navigation with Latent Goal Models
We describe a robotic learning system for autonomous navigation in diver...
read it
-
AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
Synthesizing graceful and life-like behaviors for physically simulated c...
read it
-
Benchmarks for Deep Off-Policy Evaluation
Off-policy evaluation (OPE) holds the promise of being able to leverage ...
read it
-
Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robots
Developing robust walking controllers for bipedal robots is a challengin...
read it
-
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning
Progress in deep reinforcement learning (RL) research is largely enabled...
read it
-
Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification
In the standard Markov decision process formalism, users specify tasks b...
read it
-
Maximum Entropy RL (Provably) Solves Some Robust RL Problems
Many potential applications of reinforcement learning (RL) require guara...
read it
-
PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning
We study reinforcement learning (RL) with no-reward demonstrations, a se...
read it
-
COMBO: Conservative Offline Model-Based Policy Optimization
Model-based algorithms, which learn a dynamics model from logged experie...
read it
-
Offline Model-Based Optimization via Normalized Maximum Likelihood Estimation
In this work we consider data-driven optimization problems where one mus...
read it
-
How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
Deep reinforcement learning (RL) has emerged as a promising approach for...
read it
-
SimGAN: Hybrid Simulator Identification for Domain Adaptation via Adversarial Reinforcement Learning
As learning-based approaches progress towards automating robot controlle...
read it
-
Evolving Reinforcement Learning Algorithms
We propose a method for meta-learning reinforcement learning algorithms ...
read it
-
Model-Based Visual Planning with Self-Supervised Functional Distances
A generalist robot must be able to complete a variety of tasks in its en...
read it
-
ViNG: Learning Open-World Navigation with Visual Goals
We propose a learning-based navigation system for reaching visually indi...
read it
-
Variable-Shot Adaptation for Online Meta-Learning
Few-shot meta-learning methods consider the problem of learning new task...
read it
-
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Distribution shifts can cause significant degradation in a broad range o...
read it
-
Models, Pixels, and Rewards: Evaluating Design Trade-offs in Visual Model-Based Reinforcement Learning
Model-based reinforcement learning (MBRL) methods have shown strong samp...
read it
-
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design
A wide range of reinforcement learning (RL) problems - including robustn...
read it
-
Parrot: Data-Driven Behavioral Priors for Reinforcement Learning
Reinforcement learning provides a general framework for flexible decisio...
read it
-
C-Learning: Learning to Achieve Goals via Recursive Classification
We study the problem of predicting and controlling the future state dist...
read it
-
Reinforcement Learning with Videos: Combining Offline Observations with Interaction
Reinforcement learning is a powerful framework for robots to acquire ski...
read it
-
Continual Learning of Control Primitives: Skill Discovery via Reset-Games
Reinforcement learning has the potential to automate the acquisition of ...
read it
-
Amortized Conditional Normalized Maximum Likelihood
While deep neural networks provide good performance for a range of chall...
read it
-
Rearrangement: A Challenge for Embodied AI
We describe a framework for research and evaluation in Embodied AI. Our ...
read it
-
COG: Connecting New Skills to Past Experience with Offline Reinforcement Learning
Reinforcement learning has been applied to a wide variety of robotics pr...
read it
-
Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning
We identify an implicit under-parameterization phenomenon in value-based...
read it
-
Conservative Safety Critics for Exploration
Safe exploration presents a major challenge in reinforcement learning (R...
read it
-
γ-Models: Generative Temporal Difference Learning for Infinite-Horizon Prediction
We introduce the γ-model, a predictive model of environment dynamics wit...
read it
-
One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL
While reinforcement learning algorithms can learn effective policies for...
read it
-
MELD: Meta-Reinforcement Learning from Images via Latent State Models
Meta-reinforcement learning algorithms can enable autonomous agents, suc...
read it
-
OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning
Reinforcement learning (RL) has achieved impressive performance in a var...
read it
-
LaND: Learning to Navigate from Disengagements
Consistently testing autonomous mobile robots in real world scenarios is...
read it
-
Learning Social Learning
Social learning is a key component of human and animal intelligence. By ...
read it
-
Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings
Reinforcement learning (RL) in real-world safety-critical target setting...
read it
-
Offline Meta-Reinforcement Learning with Advantage Weighting
Massive datasets have proven critical to successfully applying deep lear...
read it
-
Assisted Perception: Optimizing Observations to Communicate State
We aim to help users estimate the state of the world in tasks like robot...
read it
-
Adaptive Risk Minimization: A Meta-Learning Approach for Tackling Group Shift
A fundamental assumption of most machine learning algorithms is that the...
read it
-
Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions
This paper seeks to establish a framework for directing a society of sim...
read it
-
Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Modeling a structured, dynamic environment like a video game requires ke...
read it
-
Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?
Out-of-training-distribution (OOD) scenarios are a common challenge of l...
read it
-
Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifiers
We propose a simple, practical, and intuitive approach for domain adapta...
read it
-
Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors
The ability to predict and plan into the future is fundamental for agent...
read it
-
Simple and Effective VAE Training with Calibrated Decoders
Variational autoencoders (VAEs) provide an effective and simple method f...
read it
-
Ecological Reinforcement Learning
Much of the current work on reinforcement learning studies episodic sett...
read it
-
Learning Invariant Representations for Reinforcement Learning without Reconstruction
We study how representation learning can accelerate reinforcement learni...
read it
-
Accelerating Online Reinforcement Learning with Offline Datasets
Reinforcement learning provides an appealing formalism for learning cont...
read it
-
RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real
Deep neural network based reinforcement learning (RL) can learn appropri...
read it