Proposes CoPO, a new policy optimization method for competitive games.
problem Designing efficient optimization methods for competitive Markov decision processes.
method Competitive policy optimization (CoPO) approach that exploits game-theoretic nature of competitive games.
result Stable optimization, convergence to sophisticated strategies, and higher scores compared to baseline methods.
A drone catches another agile drone using competitive reinforcement learning.
problem Intercepting an agile drone with another agile drone.
method Formulated as a Competitive Reinforcement Learning problem, trained with PPO, using a high-fidelity simulation environment.
result Trained policies outperform common heuristic baselines in catch rate, time to catch, and crash rate.
New RL method learns value function for many policies using few key states.
problem Evaluate and improve policies in continuous control problems.
method Combines actor-critic architecture and policy embedding to learn a single value function for many policies.
result Value function minimizes prediction error by learning a small set of 'probing states' and their impact on policies' returns.
Pakistan examines digital mergers using traditional competition tools.
problem Regulating digital mergers in a developing country.
method Empirical comparative analysis of CCP's M&A decisions.
result CCP uses same decision factors for digital and traditional M&As.
Dynamic pricing policy converges to Nash equilibrium with low regret.
problem Sequential price competition among sellers over multiple periods.
method Semi-parametric least-squares estimation of s-concave demand functions.
result Prices converge to Nash equilibrium with rate O(T−1/7) and sellers incur regret O(T5/7). RL controls small soccer robots in a real league, beating human-designed policies.
problem Training robots to play complex, real-world sports.
method Sim-to-Real RL approach, training in simulated environment, applying to real-world robots.
result Robots learned policies to compete effectively, beating human-designed strategies.
We present a broad agenda for meaningful banking regulation reform aiming the creation of evolutive competitive environment to maximize the effectiveness of international financial system through the introduction of fair competition process among the banks in free market capitalism. We assume that the international fin…
Adapts model-based advice to stabilize black-box policies for nonlinear control.
problem Stabilizing machine-learned policies for nonlinear control with limited model information.
method Proposes an adaptive λ-confident policy to combine black-box and model-based advice. result Proves the stability of the adaptive λ-confident policy and its competitive ratio. New RL algorithms learn policies competitive with best in class without assuming optimal policy.
problem Agnostic RL where best policy not necessarily optimal.
method First-order optimization in non-Euclidean space, reducing to policy learning.
result Sample complexity upper bounds for three algorithms under VGD condition.
This study uses OPE methods to quickly assess auction policies.
problem Rapid decision-making in dynamic auction environments.
method Off-Policy Evaluation and counterfactual methods.
result Improved policy selection and optimization.
New algorithm improves self-play reinforcement learning for competitive games.
problem Inefficient opponent selection in self-play reinforcement learning.
method Intelligently selects opponents based on adversarial rules derived from saddle point optimization.
result Algorithm converges to approximate equilibrium with high probability in convex-concave games.
Reinforcement learning agents that operate in diverse and complex environments can benefit from the structured decomposition of their behavior. Often, this is addressed in the context of hierarchical reinforcement learning, where the aim is to decompose a policy into lower-level primitives or options, and a higher-leve…
Study model selection in batch policy optimization with three error sources.
problem Learn a policy competitive with the best model class in batch policy optimization.
method Formalized in contextual bandit setting with linear model classes, addressing approximation error, statistical complexity, and dataset shift.
result No algorithm can optimally trade-off all three error sources, but relaxing any one enables near-oracle inequalities for the others.
Paper tackles online optimization with memory and competitive control.
problem Minimizing hitting and switching costs in online optimization problems.
method Optimistic Regularized Online Balanced Descent algorithm.
result Achieves a constant, dimension-free competitive ratio.
Study minimax off-policy evaluation in multi-armed bandits with known and unknown behavior policies.
problem Evaluate policies in multi-armed bandits with unknown behavior policies.
method Develop minimax rate-optimal procedures for known and unknown behavior policies, including the Switch estimator and Chebyshev polynomial-based estimator.
result Plug-in estimator achieves optimal competitive ratio up to a logarithmic factor when behavior policy is unknown.
The real estate is a pillar industry of China's national economy. Due to changes in policy and market conditions, the real estate companies are facing greater pressures to survive in a competitive environment. They must improve their financial competitiveness. Based on the conceptual framework of financial competitiven…
MAMBA learns policies competitive with multiple conflicting oracles.
problem Learning policies from multiple conflicting oracles in reinforcement learning.
method MAMBA uses a gradient estimator in the style of GAE to optimize policies, leveraging demonstrations from multiple weak oracles.
result MAMBA outperforms the state-of-the-art in learning policies competitive with multiple conflicting oracles.
We propose a new algorithm, Mean Actor-Critic (MAC), for discrete-action continuous-state reinforcement learning. MAC is a policy gradient algorithm that uses the agent's explicit representation of all action values to estimate the gradient of the policy, rather than using only the actions that were actually executed. …
Method selects best estimator for off-policy evaluation.
problem Choosing the best estimator for off-policy evaluation.
method Generic data-driven method for estimator selection.
result Method is competitive with oracle estimator, up to a constant factor.
Optimal learning for parametric prophet inequalities with exponential-type distributions
problem Learning in prophet inequalities with unknown parameters
method Confidence-based dynamic-programming policy
result Achieves optimal asymptotic competitive ratio using online observations
A new imitation learning method uses random search for simple policies, outperforming complex models.
problem Complexity and reward dependency issues in imitation learning.
method Derivative-free optimization with simple linear policies and random search.
result The proposed method achieves competitive performance on MuJoCo locomotion tasks without a direct reward signal.
Recent successful deep reinforcement learning algorithms, such as Trust Region Policy Optimization (TRPO) or Proximal Policy Optimization (PPO), are fundamentally variations of conservative policy iteration (CPI). These algorithms iterate policy evaluation followed by a softened policy improvement step. As so, they are…
This paper evaluates financial competitiveness of Indian real estate companies using entropy method.
problem Improving financial competitiveness of Indian real estate companies in a competitive market.
method Financial competitiveness evaluation index system using key financial ratios and a scoring system.
result Companies with high scores have strong profitability and operational capacity, while those with lower scores struggle with solvency and working capital.
Greedy policy maximizes information in unknown linear systems.
problem Exploration in unknown linear dynamical systems.
method Online greedy policy maximizing information.
result Competitive performance compared to gradient-based methods.
We introduce a new algorithm for reinforcement learning called Maximum aposteriori Policy Optimisation (MPO) based on coordinate ascent on a relative entropy objective. We show that several existing methods can directly be related to our derivation. We develop two off-policy algorithms and demonstrate that they are com…
We propose a method for tackling catastrophic forgetting in deep reinforcement learning that is \textit{agnostic} to the timescale of changes in the distribution of experiences, does not require knowledge of task boundaries, and can adapt in \textit{continuously} changing environments. In our \textit{policy consolidati…
Generative neural nets learn deep policies conditioned on goals.
problem Learning optimal policies for specific goals in reinforcement learning.
method Goal-conditioned neural nets that generate deep neural policies.
result Single learned policy generator can achieve any desired return.
Improved reinforcement learning in Minecraft with human demonstrations.
problem Sample inefficiency in reinforcement learning.
method Training policy networks on human demonstrations first, then fine-tuning with reinforcement learning.
result Best agent achieved a mean score of 48 in Minecraft.
Reinforcement learning is a promising approach to learning robotics controllers. It has recently been shown that algorithms based on finite-difference estimates of the policy gradient are competitive with algorithms based on the policy gradient theorem. We propose a theoretical framework for understanding this phenomen…
Study optimal treatment assignment policies under strategic agent responses.
problem Learning optimal treatment policies with strategic agents complicates estimation.
method Dynamic model with threshold convergence to mean-field equilibrium, consistent estimator for policy gradient.
result Threshold for treatment assignment converges to mean-field equilibrium threshold under large but finite number of agents.
A new method solves bilevel optimization problems in competitive Markov games.
problem Capturing competitive structures in RL with multiple interacting policies.
method Penalty-augmented Nikaido-Isoda descent-ascent (PANDA) method.
result PANDA converges to stationary points without convexity assumptions.
We propose a novel approach to train a multi-modal policy from mixed demonstrations without their behavior labels. We develop a method to discover the latent factors of variation in the demonstrations. Specifically, our method is based on the variational autoencoder with a categorical latent variable. The encoder infer…
New findings show optimization is crucial for OPL in large action spaces.
problem Challenges in optimizing policies for large action spaces in offline contextual bandits.
method Weighed log-likelihood objectives and estimator-aware policy parametrization.
result Simple weighted log-likelihood objectives enjoy better optimization properties and recover competitive policies.
Bayesian design improves by reducing policy training cost.
problem Double intractability in expected information gain limits policy learning.
method Score matching to isolate EIG, then train policy singly intractably.
result Reduced computational burden for policy training, allowing multiple iterations.
Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric informat…
This paper proposes Self-Imitation Learning (SIL), a simple off-policy actor-critic algorithm that learns to reproduce the agent's past good decisions. This algorithm is designed to verify our hypothesis that exploiting past good experiences can indirectly drive deep exploration. Our empirical results show that SIL sig…
A framework for reinforcement learning tackles CVRP with competitive results.
problem Optimizing routes for vehicles with limited capacity.
method Formulates action selection as a mixed-integer optimization problem, uses policy iteration to improve policies.
result Achieves an average gap of 1.7% with state-of-the-art OR methods on CVRP instances.
A new method removes policy optimization in adversarial imitation learning.
problem Adversarial imitation learning's delicate alternated optimization.
method Explicitly condition discriminator on two policies, solving generator's optimization problem directly.
result Simpler approach competitive to prevalent methods.
In this study, we investigate the use of global information to speed up the learning process and increase the cumulative rewards of reinforcement learning (RL) in competition tasks. Within the actor-critic RL, we introduce multiple cooperative critics from two levels of the hierarchy and propose a reinforcement learnin…
Model-based reinforcement learning has the potential to be more sample efficient than model-free approaches. However, existing model-based methods are vulnerable to model bias, which leads to poor generalization and asymptotic performance compared to model-free counterparts. In addition, they are typically based on the…
A commonly expressed concern about the rise of the peer-to-peer rental market Airbnb is that hosts---those renting out their properties---impose costs on their unwitting neighbors. I consider the question of whether apartment building owners will, in a competitive rental market, set a building-specific Airbnb hosting p…
ZOSPI improves RL policies with global value function exploitation.
problem Limited sample efficiency of PG algorithms in RL.
method Zeroth-order supervised policy improvement, leveraging global value function estimation.
result ZOSPI achieves competitive results with remarkable sample efficiency.
RRPI improves offline RL by optimizing policies against worst-case dynamics.
problem Offline RL's performance degrades under distribution shift and transition uncertainty.
method Formulates offline RL as robust policy optimization, treating transition kernel as decision variable.
result RRPI achieves strong average performance on D4RL benchmarks, outperforming recent baselines.
PEOC uses policy entropy to detect untrained states in RL.
problem Detecting untrained states in reinforcement learning for safety.
method Policy entropy based one-class classifier.
result PEOC is highly competitive and reliable.
As the most successful variant and improvement for Trust Region Policy Optimization (TRPO), proximal policy optimization (PPO) has been widely applied across various domains with several advantages: efficient data utilization, easy implementation, and good parallelism. In this paper, a first-order gradient reinforcemen…
Most previous studies on multi-agent reinforcement learning focus on deriving decentralized and cooperative policies to maximize a common reward and rarely consider the transferability of trained policies to new tasks. This prevents such policies from being applied to more complex multi-agent tasks. To resolve these li…
US firms improve ESG performance in response to China trade shock.
problem Impact of China trade shock on US ESG performance.
method Trade policy experiment exploiting tariff changes.
result Greater import competition from China increases US firm ESG performance.
Algorithm converges to Nash equilibria in competitive games.
problem Finding Nash equilibria in decentralized, competitive Markov games.
method Decentralized Optimistic Gradient Descent/Ascent with a critic.
result Converges to the set of Nash equilibria under self-play.