APES simplifies reinforcement learning environment design in Python.
problem Creating and simulating reinforcement learning environments.
method Introduces APES, a Python toolbox for 2D grid-world environments.
result Equips reinforcement learning agents with customizable field of vision and item/reward interactions.
A machine learning environment for detecting autonomous vehicle corner cases.
problem Testing autonomous driving software in the real world is difficult.
method Connecting CARLA simulation software to TensorFlow and custom AI client software.
result The system can identify situations where AI software fails to understand the scenario.
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.
Proposes ABIDES-Gym for financial markets simulation.
problem Training multi-agent systems in financial markets.
method Wrapping DEMAS into OpenAI Gym framework.
result Developed two financial markets OpenAI Gym environments.
New method transfers robotic control policies to unknown environments using a family of policies.
problem Transfer of robotic control policies trained in simulation to real hardware is difficult due to environment differences.
method Simultaneously learns a family of policies with different behaviors; searches for the best policy based on task performance.
result Demonstrates superior performance in unknown environments compared to other methods, overcoming larger modeling errors.
A lifelong learning architecture improves reinforcement learning policies using simulations and a DNC model.
problem Improving reinforcement learning policies in dynamic environments.
method Iterative training of a Reinforcement Learning agent and a DNC model in conjunction.
result DNC models can continually learn from pixels alone to simulate new tasks.
INTAGS uses interactive simulation to improve realism in multi-agent systems.
problem Challenges in developing realistic agent-based simulators for multi-agent systems.
method INTAGS introduces a novel metric to evaluate the difference between real and synthetic multi-agent systems, optimizing a stochastic policy in reinforcement learning to adapt to interactive sequential decision-making environments.
result INTAGS generates more realistic market data compared to state-of-the-art approaches.
Models that can simulate how environments change in response to actions can be used by agents to plan and act efficiently. We improve on previous environment simulators from high-dimensional pixel observations by introducing recurrent neural networks that are able to make temporally and spatially coherent predictions f…
RecSim creates customizable simulation environments for RSs.
problem Creating realistic simulation environments for RSs.
method Configurable platform for authoring simulation environments.
result Enables pushing the limits of RL and RS techniques.
FinRL-Meta creates diverse market environments for DRL in finance.
problem Inaccurate financial data and diverse market environments challenge DRL in finance.
method Open-source data processing tools, hundreds of market environments, and multiprocessing.
result FinRL-Meta improves DRL accuracy and speed in financial simulations.
Adversarial RL recovers agent rewards from financial market data simulations.
problem Recovering agent rewards in volatile financial markets with unknown dynamics.
method Adversarial inverse reinforcement learning in latent space simulations.
result Adversarial RL can robustly recover agent rewards from latent space representations of real market data.
Paper tackles AI driving competition challenges with mixed simulation and real-world data.
problem AI algorithms perform poorly in real-world environments compared to simulated ones and vice versa.
method Employed imitation learning on a mixed dataset to train algorithms equally well in all environments.
result Trained algorithms performed well in both simulated and real-world environments.
Surrogate models speed up RL training in dynamic systems.
problem High computational cost of high-fidelity simulations.
method Developed and tested surrogate models for RL training.
result Surrogate models can significantly accelerate RL training.
Unity offers a flexible platform for AI research with rich simulations.
problem Limited configurability and complexity in existing simulation environments.
method Proposed a taxonomy of simulation platforms and demonstrated Unity's suitability.
result Unity enables rich, complex simulations for AI research.
AMUSE uses reinforcement learning to predict optimal model updates.
problem Concept drift weakens model performance over time.
method Reinforcement learning in a simulated environment.
result AMUSE proactively recommends updates based on performance improvements.
Paper tackles sim-to-real transfer in continuous domains with partial observations.
problem Lack of theoretical foundation for sim-to-real transfer in continuous domains with partial observations.
method Developed a new algorithm for infinite-horizon average-cost LQGs and established a regret bound.
result A popular robust adversarial training algorithm can learn competitive policies from simulation to real-world environments.
Deep learning agent improves pedestrian navigation in urban environments.
problem Autonomous driving among pedestrians in urban areas.
method Multi-objective deep reinforcement learning using a deep Q-learning variant.
result The multi-objective DQN agent outperforms single-objective DQN in various environments.
PPOPT uses pretraining to speed up reinforcement learning in physics simulations.
problem High computational costs and inefficiency in reinforcement learning with small training samples.
method A novel policy neural network architecture that combines pretraining and fully-connected networks.
result PPOPT outperforms classic PPO on small training samples in terms of rewards and stability.
Proposes a method for model-based RL in complex environments without perfect simulators.
problem Lack of cheap and perfect simulators in real-world tasks.
method Induces a world program by learning dynamics and actions in graph-based environments.
result World program enables complex planning tasks in environments without perfect simulators.
We present the use of the fitted Q iteration in algorithmic trading. We show that the fitted Q iteration helps alleviate the dimension problem that the basic Q-learning algorithm faces in application to trading. Furthermore, we introduce a procedure including model fitting and data simulation to enrich training data as…
RL agents optimize order execution in a realistic market simulation.
problem Optimal order execution challenges in a complex market.
method Multi-agent RL in a historical order book simulation.
result RL agents converge to TWAP strategies in some scenarios.
A new neural network model improves reinforcement learning efficiency.
problem Improving sample efficiency in reinforcement learning.
method Proposes a neural network architecture using VQ-VAE and convolutional LSTM for world modeling.
result Shows comparable performance to SimPLe with significantly smaller model.
A new neural network model simulates financial markets without assuming underlying dynamics.
problem Modeling financial time series without assuming underlying dynamics.
method Neural network based generative model using a parsimonious Variational Autoencoder framework.
result Works reliably in small data environments, providing a new performance evaluation metric.
Google Research Football: A new 3D physics-based game for reinforcement learning.
problem Training reinforcement learning algorithms in complex, realistic environments.
method Developed a new 3D physics-based football simulator environment.
result Reported baseline results for various reinforcement algorithms.
A game environment simulates competition among many agents for resources.
problem Understanding large-scale multiagent interactions and resource competition.
method Developed a persistent, massively multiplayer AI environment.
result Population size affects the development of skillful behaviors and niche differentiation.
Bayesian segmentation and uncertainty estimation improve 3D model accuracy for factory planning.
problem Generating accurate 3D models from outdated and incomplete 2D data.
method Bayesian neural network for point cloud segmentation and entropy-based uncertainty estimation.
result Bayesian segmentation network significantly improves model accuracy and object identification.
Solvents can induce helical knots in simulated biopolymer tubes.
problem Understanding how solvents influence the folding of biopolymers.
method Computer simulations using morphometric solvation techniques.
result Solvents can induce complex helical structures, including knots.
Study on variance of policy gradient in simple RL environments.
problem Understanding variance of policy gradient estimators in continuous RL.
method Analyzes REINFORCE estimator in linear-quadratic environments with Gaussian noise.
result Derives and validates bounds on estimator variance empirically.
Agent learns policies from world models in simulated environments.
problem Training reinforcement learning agents in diverse environments.
method Generative neural network models environments, compact policies evolved from features.
result Achieves state-of-the-art performance across various environments.
Method adapts policies for new environments efficiently.
problem Difficulties in transferring reinforcement learning policies to new environments.
method Variational Policy Embedding (VPE) learns latent variables and a master policy.
result Policies can quickly adapt to new environments in latent space.
JAX MD enables differentiable physics simulations for molecular dynamics.
problem Performing efficient and differentiable physics simulations for molecular dynamics.
method Differentiable physics simulation environments, interaction potentials, neural networks, flexible primitives.
result Differentiable physics simulations can be used for meta-optimization and scaling to large particle systems.
LLMs can simulate human investment attitudes based on personality traits.
problem Investigating how LLMs mimic human investment behaviors.
method Simulated investment task using LLM personas with specific Big Five personality profiles.
result LLMs can produce meaningful behavioural differences in investment tasks that align with human traits.
Study simulates liquidity in fractional ownership markets using ABM.
problem Understanding liquidity dynamics in illiquid markets.
method Agent-based modeling (ABM) with empirical data.
result Simulation reveals insights into market structures and trading behaviors.
Imaginative RL uses GANs to simulate real environments, making RL more efficient.
problem Lack of data efficiency and safety constraints in reinforcement learning.
method Generative Adversarial Imaginative Reinforcement Learning (GAIL) algorithm.
result The proposed algorithm more efficiently utilizes real-world experience.
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.
Self-supervised policy adapts after deployment without rewards.
problem Generalizing reinforcement learning policies across different environments.
method Uses self-supervision to train policies in new environments without reward signals.
result Significant improvements in generalization across diverse environments.
DIVA generates diverse tasks for complex simulators, enabling adaptive agent training.
problem Lack of diverse training data for complex, open-ended simulators.
method Evolutionary approach using domain randomization and procedural generation.
result Successfully trains adaptive agent behavior in complex simulators.
A method to learn robust policies for environments with model mismatches.
problem Training agents in high-stakes scenarios with mismatched training and real environments.
method Formalizes the perturbation as a zero-sum game to find Nash Equilibrium, which corresponds to the robust policy.
result Our algorithm can find a near-optimal robust policy with high probability using polynomial samples.
Bayesian optimisation has been successfully applied to a variety of reinforcement learning problems. However, the traditional approach for learning optimal policies in simulators does not utilise the opportunity to improve learning by adjusting certain environment variables: state features that are unobservable and ran…
The ability to generalize is an important feature of any intelligent agent. Not only because it may allow the agent to cope with large amounts of data, but also because in some environments, an agent with no generalization capabilities cannot learn. In this work we outline several criteria for generalization, and prese…
StockAgent uses AI to simulate real-world stock trading, analyzing external factors and profitability.
problem Investors need to understand how external factors affect stock trading.
method Developed StockAgent, a multi-agent system driven by large language models.
result Identified how external factors impact trading behavior and profitability.
RadioUNet uses deep learning to estimate pathloss in urban environments.
problem Accurate pathloss estimation for urban environments.
method Deep neural networks trained on physical simulation data.
result RadioUNet generates pathloss estimations faster and more accurately than existing methods.
MarS simulates financial markets using generative models.
problem Simulating realistic financial market effects.
method Order-level generative foundation model (LMM) for realistic, interactive, and controllable order generation.
result Strong scalability and robust realism in MarS.
DyFEn simulates blockchain for fee setting in payment channels.
problem Dynamic fee setting in off-chain payment channels.
method Agent-based reinforcement learning in a blockchain simulation.
result Empirical results of reinforcement learning methods on dynamic fee setting.
Neural MMO simulates MMOs to study multiagent intelligence.
problem Limited research environments for multiagent intelligence.
method Developed a new game environment inspired by MMOs.
result Standard methods can learn interesting behaviors in MMOs.
Paper simplifies deep RL for mobile robots on consumer hardware.
problem Training complex reasoning agents in 3D environments.
method Used ViZDoom for fast simulation and varied difficulty scenarios.
result Robust baseline agent architecture trained on consumer hardware.
Proposes a method to improve reinforcement learning in multi-view environments.
problem Improving policy learning in environments with partial observability.
method Actor-Critic-Attention Mechanism for generating a single feature representation from multiple views.
result Our method outperforms state-of-the-art baselines on various complex 3D environments.
Band-limited SAC improves learning efficiency and stability in simulated environments.
problem Improving sample efficiency and stability in SAC algorithms.
method Artificially bandlimiting the target critic's spatial resolution using a convolutional filter.
result Bandlimited SAC outperforms classic twin-critic SAC in various Gym environments and is more stable.