LEADS improves model generalization across different environments.
problem Modeling dynamical systems from varied environments leads to biased or scarce solutions.
method LEADS learns a shared model capturing common dynamics and additional terms for environment-specific dynamics.
result LEADS improves model generalization for both known and novel environments.
New algorithms reduce dynamic regret in non-stationary RL environments.
problem Optimizing policies in environments that change over time.
method POWER and POWER++ algorithms for policy optimization with dynamic regret analysis.
result POWER++ improves dynamic regret by actively adapting to non-stationarity.
Proposes a method to improve few-shot transfer in off-dynamics RL.
problem Traditional RL struggles with transferring policies between environments with different dynamics.
method Introduces a penalty to regulate source-trained policies in target environments with limited data.
result Improves performance in various off-dynamics RL scenarios compared to existing methods.
MAOP learns object dynamics from raw visual data.
problem Efficient learning of dynamics from raw visual data for multiple objects.
method Three-level learning architecture with spatial-temporal relational reasoning.
result Significantly outperforms previous methods in sample efficiency and generalization.
Universal online optimization for dynamic environments using uniclass prediction.
problem Online optimization in changing environments with dynamic regret.
method Reduces dynamic online optimization to uniclass prediction problem, allowing control over dynamic regret bounds.
result First paper with state-of-the-art dynamic regret guarantees for general convex cost functions.
Proposes learning task-agnostic dynamics priors for faster RL.
problem Challenges in learning accurate dynamics models for RL.
method Pre-training a frame predictor on physics videos to initialize and fine-tune dynamics models.
result Improves policy learning and convergence, outperforming competitors.
MANGA transfers policies across environments with varying dynamics and noise.
problem Transferring policies across multiple environments with different dynamics and motor noise.
method Decouples policy learning from system identification, trains dynamics-conditioned policies, and learns dynamics parameters from rollouts.
result Demonstrates effective transfer of learned policies across four MuJoCo agents using agnostic RL and imitation learning methods.
We introduce a new local regret framework for non-convex models in dynamic environments.
problem Challenges in online forecasting for non-convex models with frequent updates and concept drift.
method We propose a novel local regret framework and a time-smoothed gradient update rule.
result Our approach yields more stable, robust, and computationally efficient forecasting compared to state-of-the-art methods.
A framework for learning disentangled representations of symmetric environments.
problem Discovering and modelling the underlying structure of environments.
method Group representation theory for disentangled representations of dynamical environments.
result Our method enables accurate long-horizon predictions and correlates with disentanglement quality.
Modular method predicts motion in crowded scenes using learned environment models.
problem Predicting motion in dynamic, crowded environments.
method Modular model of spatial and dynamic aspects, unsupervised adaptation to new tasks.
result Comparable performance to state-of-the-art, transferable across tasks.
The paper proposes a method to improve reinforcement learning by ensuring consistency between observed and imagined dynamics.
problem Compounding errors in traditional model-based reinforcement learning approaches.
method An auxiliary cost function to ensure consistency between observed and imagined dynamics.
result The proposed approach helps train powerful policies and better dynamics models.
New method improves RL/IL agents' adaptability to unseen environments.
problem Current RL/IL techniques struggle with generalizing to unseen environments.
method Zero-shot compositional policy learning with multi-modal fusion and attention mechanism.
result Language grounding enhances generalization across varied environments.
HySRL improves RL sample efficiency with shifted-dynamics data.
problem Leveraging historical data with shifted dynamics to improve sample efficiency in RL.
method HySRL, a hybrid transfer RL algorithm that uses prior information on dynamics shift to achieve better sample complexity.
result HySRL achieves problem-dependent sample complexity and outperforms pure online RL.
Method learns attractive areas from agent motions to represent environments.
problem Representing environments based on moving agents' nonlinear motions.
method Switching model of velocity fields, parametric representation of attractive spots.
result Dynamic map of attractive areas for online learning.
We demonstrate the use of conditional autoregressive generative models (van den Oord et al., 2016a) over a discrete latent space (van den Oord et al., 2017b) for forward planning with MCTS. In order to test this method, we introduce a new environment featuring varying difficulty levels, along with moving goals and obst…
New model predicts dynamic volatility in uncertain financial markets.
problem Predicting dynamic volatility in financial markets with uncertainty.
method Generalized Barndorff-Nielsen and Shephard (BN-S) model considering delay and fuzziness.
result Effective prediction of dynamic volatility with improved performance.
Deep RL agent improves lane changing in unpredictable traffic.
problem Uncertainty in other drivers' behaviors and safety vs agility trade-off.
method Developed a deep reinforcement learning agent in a simulated highway environment.
result Significantly better performance in noisy environments compared to heuristic methods.
New pricing algorithm learns demand curves and optimizes prices in dynamic markets.
problem Dynamic pricing in markets with incomplete demand information and shifting conditions.
method Actor-Critic Information-Directed Pricing (ACIDP) using IDS algorithms and auditing procedures.
result ACIDP outperforms UCB and TS in market environment shifts.
New algorithms reduce dynamic regret for convex and smooth functions in non-stationary environments.
problem Online convex optimization in non-stationary environments.
method Proposed novel online algorithms exploiting smoothness to reduce dynamic regret.
result Dynamic regret improved to O ( T ) \mathcal{O}(T) O ( T ) for convex and smooth functions. HRM-Agent learns to navigate dynamic mazes using reinforcement learning.
problem Training HRM in dynamic, uncertain, partially observable environments.
method Reinforcement learning to train HRM-Agent.
result HRM-Agent successfully learns to navigate dynamic mazes.
Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment. These methods are sample efficient and facilitate learning in the real world but fail to generalize to subtle variations in the underlying dynamics, e.g., due to differences in mass, friction, or actuators a…
A new method learns to prioritize and use multiple views of an environment for better decision-making.
problem Learning from multiple views of an environment to improve decision-making.
method Attention-based deep reinforcement learning to dynamically attend to views of the environment.
result The method improves performance in complex 3D environments with obstacles.
Causal models help ensure fairness in systems with changing environments.
problem Ensuring fairness in systems with dynamic, long-term effects.
method Causal directed acyclic graphs (DAGs) to model fairness and manipulate causal assumptions.
result Causal assumptions enable simulation and off-policy estimation of interventions.
This work uses reinforcement learning to optimize task scheduling and execution in a dynamic multi-agent warehouse environment.
problem Optimizing task scheduling and execution in a dynamic multi-agent warehouse environment with limited observability.
method Deep reinforcement learning to solve both high-level scheduling and low-level multi-agent execution problems.
result Demonstrates the effectiveness of reinforcement learning in optimizing task scheduling and execution in a dynamic multi-agent environment.
Kernel-based methods exhibit well-documented performance in various nonlinear learning tasks. Most of them rely on a preselected kernel, whose prudent choice presumes task-specific prior information. Especially when the latter is not available, multi-kernel learning has gained popularity thanks to its flexibility in ch…
Efficiently learn and adapt to multiple tasks with limited samples.
problem Efficiently learn and adapt to multiple tasks with limited samples.
method Learn a dynamical model during training and use it for sample-efficient adaptation at test time.
result Significantly fewer samples required for adaptation to new tasks.
Transformers achieve near-optimal dynamic regret in non-stationary reinforcement learning.
problem Understanding and handling non-stationary environments in reinforcement learning.
method Demonstrated that transformers can achieve nearly optimal dynamic regret bounds in non-stationary settings.
result Transformers can approximate and learn strategies for non-stationary environments, matching or outperforming existing expert algorithms.
We describe theoretical bounds and a practical algorithm for teaching a model by demonstration in a sequential decision making environment. Unlike previous efforts that have optimized learners that watch a teacher demonstrate a static policy, we focus on the teacher as a decision maker who can dynamically choose differ…
Meta-learning improves drone trajectory design for dynamic wireless networks.
problem Designing optimal trajectories for energy-constrained drones in dynamic network environments.
method Proposes a meta-learning algorithm to adaptively tune a reinforcement learning solution for trajectory design.
result Meta-tuned RL yields faster convergence and improved communication performance compared to baseline algorithms.
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especiall…
Bayesian Federated Learning improves model reliability in dynamic environments.
problem Uncertainty quantification and robust adaptation in distributed learning.
method Proposes a continual BFL framework using SGLD for sequential updates and continual learning challenges.
result Continual Bayesian updates preserve knowledge and adapt to evolving data.
Survey of RL algorithms for dynamic environments.
problem Handling changing operating conditions in RL.
method Survey of algorithms developed for non-stationary environments.
result Methods to adapt to varying operating conditions.
New algorithm reduces dynamic regret in non-stationary BCO problems.
problem Sequential decision-making with non-stationary environments.
method Proposes a novel algorithm for dynamic regret measurement.
result Achieves optimal dynamic regret for one-point and two-point feedback models.
CoDA adapts dynamics models to new physical systems by conditioning on context.
problem Generalizing to new physical systems with shared dynamics but different contexts.
method Context-informed dynamics adaptation (CoDA) using multiple environments and a hypernetwork.
result State-of-the-art generalization results on nonlinear dynamics.
This work develops agents to learn generalizable policies for dynamic network environments.
problem Real-world network topologies change due to attackers, defenders, or system failures, leading to failures in adaptive ACD systems.
method Developing agents to learn generalizable policies across dynamic network environments.
result Agents can learn robust policies for dynamic network topologies and diverse attackers.
Selective reinitialization improves adaptability of neural bandits in dynamic environments.
problem Loss of plasticity in neural bandits, leading to rigid neural network parameters.
method Selective Reinitialization (SeRe) framework that dynamically resets underutilized units.
result SeRe enhances adaptability of CNB algorithms, reducing cumulative regret in dynamic environments.
In this paper, we study online convex optimization in dynamic environments, and aim to bound the dynamic regret with respect to any sequence of comparators. Existing work have shown that online gradient descent enjoys an O ( T ( 1 + P T ) ) O(\sqrt{T}(1+P_T)) O ( T ( 1 + P T )) dynamic regret, where T T T is the number of iterations and P T P_T P T is the path-le…
NoRML adapts RL policies without explicit rewards.
problem Adapting to new environments without external reward feedback.
method Extends MAML for RL using observable dynamics instead of reward.
result NoRML outperforms MAML in dynamic task adaptation.
CARL controls a quadruped to move naturally in complex environments.
problem Motion synthesis in dynamic environments with complex constraints.
method CARL uses GANs to adapt high-level controls to action distributions and deep reinforcement learning for dynamic recovery.
result CARL can be controlled with high-level directives and react naturally to dynamic environments.
DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.
problem Efficiently discovering targets in partially observable environments with limited sampling.
method DiffATD uses diffusion dynamics to maintain a belief distribution over unobserved states, balancing exploration and exploitation.
result DiffATD outperforms baselines and supervised methods in diverse domains.
New method learns adaptive exploration strategies for dynamic tasks.
problem Learning effective exploration strategies in changing environments.
method Informed policy regularization to reduce sample complexity of RNN-based policies.
result Method learns efficient exploration strategies balancing information gathering and reward maximization.
Proposes DLGPD model to learn dynamics from images for planning.
problem Planning in unknown, indirectly observable environments.
method Deep latent Gaussian process dynamics model trained jointly with neural networks.
result Demonstrates improved data efficiency and transfer learning.
This paper shows that explicitly learning motion improves reinforcement learning in dynamic environments.
problem Learning controllers for dynamic environments without explicit motion representation.
method Explicitly learning motion representation using image difference or temporal stacks of frames.
result Explicit motion learning improves the quality of learned controllers in dynamic scenarios.
The study questions the necessity of accurate models in MBRL.
problem The difficulty of achieving and utilizing accurate models in complex or changing environments.
method Introduces a meta-learning algorithm focused on model usefulness rather than accuracy.
result Meta-learning models enable faster learning than accurate models built with domain-specific knowledge.
New algorithms optimize decisions in changing environments with dynamic regret bounds.
problem Optimizing decisions in non-stationary settings like dynamic pricing and traffic routing.
method Sliding window-upper confidence bound algorithm and bandit-over-bandit framework.
result Achieves optimal dynamic regret bounds for non-stationary bandit problems.
Proposes a method to learn policies from offline data with reduced bias.
problem Learning policies from offline data with reduced bias and complexity constraints.
method Cross-fitted debiasing device for policy learning from offline data.
result Achieves N \sqrt N N regret for complex policy classes with a product-of-errors nuisance remainder. To maximize its success, an AGI typically needs to explore its initially unknown world. Is there an optimal way of doing so? Here we derive an affirmative answer for a broad class of environments.
Optimally explores dynamical systems with varying properties using context inference.
problem Learning dynamics models for systems with varying properties.
method Formulates dynamics models as stochastic processes conditioned on a latent context variable inferred from system transitions. Uses probabilistic formulation to compute optimal action sequences for exploration.
result Demonstrates effectiveness of the method on non-linear toy-problems and reinforcement learning environments.