Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,742 papers · 148 categories

Trend · papers per month

3468101135 · Jun 202019922001200920172026
48 results for agent manipulation

Modified Perceptron handles strategic agents with limited position changes.

problem Learning linear classifiers in the presence of strategic agents that can manipulate their positions.
method Developed a modified Perceptron algorithm with bounded mistakes under various manipulation costs.
result The modified Perceptron achieves bounded mistakes even when manipulation costs are unknown.

When consequential decisions are informed by algorithmic input, individuals may feel compelled to alter their behavior in order to gain a system's approval. Models of agent responsiveness, termed "strategic manipulation," analyze the interaction between a learner and agents in a world where all agents are equally able …

2018-08-27abs ↗pdf ↗

RL agent outperforms model-based approach in detecting price manipulation.

problem Detecting and exploiting price manipulation opportunities.
method Compared model-free RL with model-based approach in a market with Almgren-Chriss framework.
result RL consistently outperforms model-based approach, especially with noisy parameter estimates.

This work tackles force control for contact-rich manipulation tasks with rigid robots using RL.

problem Challenges in working with real robotic hardware, especially position-controlled robots.
method Combines RL with traditional force control techniques, implementing parallel position/force control and admittance control.
result Validated methods on both simulation and real robot (UR3 e-series) for force control.

Study cyber-attacks on RL algorithms, focusing on cost signal manipulation.

problem Adversarial manipulation of cost signals in reinforcement learning.
method Quantitative analysis of TD(λλ) and QQ-learning algorithms under manipulation.
result Bound on approximation error for TD(λλ) and convergence properties for QQ-learning under stealthy attacks.

MaskGAN fills in text blanks more flexibly and effectively.

problem Handling complex manipulations on given tokens in conditional text generation.
method Decomposed conditional text generation into make-a-blank and fill-in-the-blank tasks, and used hierarchical multi-agent reinforcement learning.
result The model produces realistic texts without compromising quality and diversity.

Malicious agents can manipulate linear contextual bandits to pull desired arms with logarithmic overhead.

problem Malicious attacks on linear contextual bandit algorithms in various domains.
method Study and propose an efficient algorithm to perform adversarial attacks on linear contextual bandits.
result Malicious agents can force a linear contextual bandit algorithm to pull any desired arm To(T)T - o(T) times over a horizon of TT steps with logarithmic modifications.

Agent-based market shows herding cycles with square-root price impact.

problem Understanding herding cycles in agent-based markets.
method Agent-based model with 20,000 retail traders interacting with a single institutional agent.
result Agent discovers multi-cycle predatory strategy with 8-11 complete cycles over 2000 trading days.

Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such reward definition makes traditional reinforcement learning algorithms very inefficien…

2019-06-10abs ↗pdf ↗

New algorithm combines curriculum learning with HER for complex object manipulation tasks.

problem Learning complex sequential object manipulation tasks from scratch is challenging.
method Curriculum learning with Hindsight Experience Replay (HER) for recurrent object manipulation tasks.
result Significant improvement in learning sequential object manipulation tasks compared to vanilla-HER.

Strategic feature manipulation helps learners identify meaningful variables in online regression settings.

problem Strategic feature manipulation poses a challenge for learners in online regression settings.
method Investigates how strategic feature manipulation by individuals can help learners recover meaningful features.
result Simple learner behavior can help accurately recover meaningful features and incentivize feature improvement.

The study examines how backrun auctions can protect traders from price manipulation.

problem Price manipulation by arbitrageurs in batched trading venues.
method Developed a laminated queueing model to study price manipulation and introduced a price manipulation coefficient.
result Bound the price manipulation coefficient and found it approximated by a 'zeta value' with measurable parameters.

When encountering novel objects, humans are able to infer a wide range of physical properties such as mass, friction and deformability by interacting with them in a goal driven way. This process of active interaction is in the same spirit as a scientist performing experiments to discover hidden facts. Recent advances i…

2016-11-06abs ↗pdf ↗

CausalWorld benchmarks robotic manipulation tasks with causal structure for transfer learning.

problem Challenges in transferring learned skills to new robotic manipulation environments.
method Proposes a simulation-based benchmark with a combinatorial family of tasks.
result Demonstrates the feasibility of tasks in the benchmark and provides baseline results.

This work improves RL for complex robotic tasks by guiding exploration with task-specific goal distributions.

problem Solving long-horizon, complex sequential tasks in robotics with sparse rewards.
method Extends hindsight relabelling to task-specific goal distributions using a small set of demonstrations.
result Significantly higher overall performance on complex robotic manipulation tasks.

In many reinforcement learning tasks, the goal is to learn a policy to manipulate an agent, whose design is fixed, to maximize some notion of cumulative reward. The design of the agent's physical structure is rarely optimized for the task at hand. In this work, we explore the possibility of learning a version of the ag…

2018-10-09abs ↗pdf ↗

Shaping in humans and animals has been shown to be a powerful tool for learning complex tasks as compared to learning in a randomized fashion. This makes the problem less complex and enables one to solve the easier sub task at hand first. Generating a curriculum for such guided learning involves subjecting the agent to…

2019-05-17abs ↗pdf ↗

We consider model-based reinforcement learning (MBRL) in 2-agent, high-fidelity continuous control problems -- an important domain for robots interacting with other agents in the same workspace. For non-trivial dynamical systems, MBRL typically suffers from accumulating errors. Several recent studies have addressed thi…

2019-01-29abs ↗pdf ↗

New algorithms optimize decision rules in strategic scenarios, minimizing prediction risk and incentivizing better outcomes.

problem Strategic agents manipulate features to improve outcomes, complicating decision-making models.
method Efficient algorithms for learning decision rules that minimize prediction risk, incentivize better outcomes, and estimate true model coefficients.
result Optimal decision rules can be learned through testing and observing agent responses, circumventing hardness results.

Paper tackles multi-object reinforcement learning, improving skill extrapolation.

problem Learning robust manipulation tasks in multi-object settings.
method Introduces a linear relation network module to enhance skill generalization.
result Agents can extrapolate and generalize to any new object number, scaling linearly.

Algorithm learns optimal coordination for strategic agents in uncertain settings.

problem Optimizing rewards for strategic agents with private types and actions.
method Combines delaying mechanism, reward angle estimation, and LinUCB algorithm.
result Near optimal regret bound of O~(T)\tilde{O}(\sqrt{T}) for learning optimal policy.

We propose Scheduled Auxiliary Control (SAC-X), a new learning paradigm in the context of Reinforcement Learning (RL). SAC-X enables learning of complex behaviors - from scratch - in the presence of multiple sparse reward signals. To this end, the agent is equipped with a set of general auxiliary tasks, that it attempt…

2018-02-28abs ↗pdf ↗

Framework for multi-agent RL with human feedback in a Snake game.

problem Improving multi-agent reinforcement learning with human feedback.
method Developed a simulated game environment for offline model training and online competitions. Introduced HILL methods and reward manipulation heuristics.
result Agents with HILL methods outperform those without in online competitions.

Attackers can significantly reduce team rewards in cooperative multi-agent reinforcement learning.

problem Robustness of cooperative multi-agent reinforcement learning to adversaries.
method Novel attack method involving training a policy network and using targeted adversarial examples.
result Reduces team reward from 20 to 9.4 by attacking a single agent, reducing winning rate from 98.9% to 0%.

Physics-informed GCRL tackles sparse feedback learning with hybrid dynamics.

problem Sparse feedback learning with high-dimensional, hybrid, or contact-dependent dynamics.
method Introduces physics-informed inductive biases into goal-conditioned value learning.
result Contact-rich manipulation tasks degrade existing Pi-GCRL methods.

A new reinforcement learning method uses mutual information to encourage agents to control their environment.

problem Learning from internal drives instead of external rewards.
method Formulate an intrinsic objective as mutual information between goal states and controllable states, derive a surrogate objective for efficient optimization.
result Demonstrated the efficacy of the approach in robotic tasks.

CAZSL learns to generalize physical interactions from context.

problem Designing models that can generalize over unknown objects during manipulation.
method Context-aware zero-shot learning using Siamese network architecture, embedding space masking, and regularization.
result CAZSL models can generalize to different parameters or features of interacting objects.

The paper proposes a method to learn from both simulation and real-world data.

problem Training autonomous systems in simulation and applying them to real-world environments.
method Balancing samples from simulation and real-world data using a replay buffer.
result The method achieves better performance in real-world tasks compared to training only in simulation.

Attackers can poison environments to force RL agents to follow target policies.

problem Security threat to reinforcement learning where attackers manipulate environments to force agents into following target policies.
method Optimization framework for finding optimal stealthy attacks under different measures of attack cost.
result Attackers can easily succeed in teaching any target policy to RL agents under mild conditions.

In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning. However, the collected trajectories can easily be imbalanced with respect to the achieved goal states. The problem of learning from imbalanced data is a well-known problem in supervised…

2019-02-20abs ↗pdf ↗

A framework disentangles controllable objects from visual signals for improved RL.

problem Improving sample efficiency and game performance in vision-based RL.
method Action-conditioned video prediction to disentangle controllable objects.
result Improved sample efficiency and game performance in Atari games.

Study intrinsic motivation for synergistic tasks in reinforcement learning.

problem Sparse-reward synergistic tasks where multiple agents must work together.
method Propose incentivizing actions that affect the world in ways not achievable individually, using either true states or a dynamics model.
result Our approach yields more efficient learning than typical methods.