New GFlowNet training framework using policy gradients for combinatorial object generation.
problem Training efficiency and robustness in GFlowNet models.
method Policy-dependent rewards and coupled training strategy for forward and backward policies.
result Advanced RL perspectives for robust gradient estimation improve GFlowNet performance.
Deriving and applying Proximal Policy Optimization to GFlowNets for efficient training of discrete sampling policies
problem Training stochastic policies to sample from structured discrete probability distributions
method Deriving policy gradient algorithms for GFlowNets and applying Proximal Policy Optimization
result Improved convergence speed and data efficiency compared to standard GFlowNet training objectives
Study on adversarial training's impact on deep neural reinforcement learning policies.
problem Vulnerability of deep neural reinforcement learning policies to imperceptible adversarial perturbations.
method Two parallel approaches: Fourier spectrum analysis and feature sensitivity measurement.
result Adversarially trained policies are more sensitive to low frequency perturbations.
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.
This work improves policy-based training by proposing an evaluation balance objective for GFlowNets.
problem Reliable estimation of policy divergence under directed acyclic graphs remains challenging.
method Proposes an evaluation balance objective over partial episodes to measure policy divergence and improve policy-based training reliability.
result Evaluation balance strengthens policy-based training reliability and broadens its flexibility.
Adapts GRPO for off-policy RL, improving reward.
problem Improving training stability and efficiency in RL.
method Adapts GRPO to off-policy setting, uses clipped surrogate objectives.
result Off-policy GRPO outperforms on-policy GRPO in empirical tests.
Deep RL policies are vulnerable to adversarial perturbations, but vanilla training yields more robust policies.
problem Vulnerability of deep reinforcement learning policies to adversarial perturbations.
method Analysis of deep reinforcement learning policy landscape and comparison of vanilla vs. adversarial training.
result Vanilla training yields more robust policies compared to adversarial training.
In recent years, state-of-the-art game-playing agents often involve policies that are trained in self-playing processes where Monte Carlo tree search (MCTS) algorithms and trained policies iteratively improve each other. The strongest results have been obtained when policies are trained to mimic the search behaviour of…
Framework improves policy generalizability under biased training data.
problem Learning policies that generalize to a target population from biased training data.
method Characterizes sample selection bias using a selection variable, optimizes minimax value over uncertainty set, derives efficient algorithm.
result Policies generalize to target population, outperform standard methods.
Simplifies RL training with fewer techniques, reducing bias and instability.
problem Training instabilities and high sample complexity in RL.
method Introduced a simple deterministic policy gradient, used propensity estimation, and delayed policy updates.
result Improved performance and reduced sample complexity through these techniques.
Computer simulation provides an automatic and safe way for training robotic control policies to achieve complex tasks such as locomotion. However, a policy trained in simulation usually does not transfer directly to the real hardware due to the differences between the two environments. Transfer learning using domain ra…
Deep reinforcement learning (DRL) on Markov decision processes (MDPs) with continuous action spaces is often approached by directly training parametric policies along the direction of estimated policy gradients (PGs). Previous research revealed that the performance of these PG algorithms depends heavily on the bias-var…
HO2 learns options from data efficiently, improving robot manipulation tasks.
problem Learning options from raw pixel inputs in 3D robot manipulation tasks.
method HO2 infers likely option choices and trains all policy components off-policy.
result HO2 outperforms existing methods on 3D robot manipulation tasks.
We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading to an unstable training process. To address this issue, we propose a new method, …
New method speeds up lifelong learning of complex tasks.
problem Catastrophic forgetting in lifelong learning.
method Directly trains lifelong function approximators via policy gradients.
result Faster convergence and better policies achieved.
Paper analyzes convergence of dynamic policy gradient for MDPs, improving performance in finite-time problems.
problem Optimal policies in finite-time MDPs are not stationary and require epoch-specific training.
method Introduces dynamic policy gradient combining dynamic programming and policy gradient, analyzes convergence for softmax parametrisation.
result Dynamic policy gradient training exploits finite-time structure, leading to better convergence bounds.
Improves reinforcement learning policies for robustness.
problem Lack of robustness in reinforcement learning policies.
method Risk-aware Distributional Reinforcement Learning (SDPG) with CVaR.
result Risk-averse policies achieve robustness against disturbances.
Learning Rate (LR) is an important hyper-parameter to tune for effective training of deep neural networks (DNNs). Even for the baseline of a constant learning rate, it is non-trivial to choose a good constant value for training a DNN. Dynamic learning rates involve multi-step tuning of LR values at various stages of th…
Paper tackles reinforcement learning generalization through invariant policy optimization.
problem Learning policies that generalize beyond training domains.
method Invariant policy optimization principle and novel learning algorithm IPO.
result Significant improvements in generalization performance on unseen domains.
End-to-end policy learning method improves CATE estimation.
problem Learning optimal treatment policies from partially observed data.
method Modified causal forest for policy learning.
result Maximizing policy value is equivalent to minimizing CATE.
PPG separates policy and value function training phases for better reinforcement learning efficiency.
problem Challenges in traditional reinforcement learning methods for policy and value function optimization.
method Integrates Phasic Policy Gradient framework that splits policy and value function training into distinct phases.
result Significantly improves sample efficiency on Procgen Benchmark compared to PPO.
Hybrid RL algorithm combines offline and online data for robust and efficient policy learning.
problem Combining robust on-policy methods with efficient offline data for hybrid RL.
method Integrates off-policy training on offline data into on-policy NPG framework.
result Achieves state-of-the-art theoretical guarantees and maintains on-policy NPG guarantees.
For training the sequence-to-sequence voice conversion model, we need to handle an issue of insufficient data about the number of speech pairs which consist of the same utterance. This study experimentally investigated the effects of Mel-spectrogram augmentation on training the sequence-to-sequence voice conversion (VC…
Modyn automates continuous ML model training on growing datasets.
problem Continuous model retraining is costly and impractical.
method Data-centric ML platform with policies for continuous training.
result Modyn enables high throughput training with sample-level data selection.
RL agents fail to generalize to unseen environments, even when dynamics are similar.
problem RL agents fail to generalize to unseen environments despite similar dynamics.
method Analyzed policy learning in POMDPs, formalized training dynamics as instances, and introduced a shared belief representation over an ensemble of specialized policies.
result Maximizing rewards induces instance-specific policies that are suboptimal on the training set.
PBVFs generalize across policies using learned value functions.
problem RL algorithms forget information about old policies when updating value functions to track the learned policy.
method Introduce Parameter-Based Value Functions (PBVFs) that include policy parameters in their inputs, enabling them to generalize across different policies.
result PBVFs enable zero-shot learning of new policies that outperform any policy seen during training.
We propose a novel approach to address one aspect of the non-stationarity problem in multi-agent reinforcement learning (RL), where the other agents may alter their policies due to environment changes during execution. This violates the Markov assumption that governs most single-agent RL methods and is one of the key c…
POLAR learns efficient data acquisition policies using pretrained belief representations.
problem Challenges in learning effective policies for adaptive data acquisition.
method POLAR decouples representation learning from policy learning by leveraging pretrained predictive foundation models as belief-state encoders.
result POLAR outperforms state-of-the-art methods across diverse tasks while requiring fewer training samples.
In this paper, we point out a fundamental property of the objective in reinforcement learning, with which we can reformulate the policy gradient objective into a perceptron-like loss function, removing the need to distinguish between on and off policy training. Namely, we posit that it is sufficient to only update a po…
PS framework selects best policy from library for CSO problems.
problem Policy selection in CSO with heterogeneous performance across covariate space.
method PS framework constructs library of candidate policies and learns a meta-policy to select the best one.
result PS consistently outperforms best single policy in heterogeneous CSO problems.
Hierarchies of temporally decoupled policies present a promising approach for enabling structured exploration in complex long-term planning problems. To fully achieve this approach an end-to-end training paradigm is needed. However, training these multi-level policies has had limited success due to challenges arising f…
A new algorithm trains experts to safely guide agents in partially observed environments.
problem Existing imitation learning methods for POMDPs can lead to sub-optimal or unsafe policies.
method Derive an objective to encourage the expert to maximize the agent's reward, then use it to train both expert and agent.
result The algorithm produces an expert policy that the agent can safely imitate, outperforming fixed expert policies.
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.
Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of…
Protects proprietary policies from imitation learning by training adversarial policy ensembles.
problem Protecting policies from external observers cloning them.
method Introduces a reinforcement learning framework that trains an ensemble of near-optimal policies, making demonstrations useless for external observers.
result Demonstrates the existence of 'non-clonable' ensembles and provides a solution to the optimization problem.
Batch Reinforcement Learning (Batch RL) consists in training a policy using trajectories collected with another policy, called the behavioural policy. Safe policy improvement (SPI) provides guarantees with high probability that the trained policy performs better than the behavioural policy, also called baseline in this…
New method uses variational inference to handle confounding in imitation learning.
problem Confounding due to different sensory inputs between expert and imitating agent.
method Train variational inference model to infer expert's latent information and use for latent-conditional policy training.
result Algorithm converges to correct interventional policy and achieves asymptotically optimal performance.
Softmax policy gradient achieves global optimality in wide neural networks with entropy regularization.
problem Optimizing softmax policies with neural networks in the mean-field regime.
method Modeling neural networks as Wasserstein gradient flows and proving global optimality of fixed points.
result Global optimality of softmax policy gradient in wide single hidden layer neural networks with entropy regularization.
Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous research showed that effective learning in complex multi-agent systems demands fo…
While deep reinforcement learning has successfully solved many challenging control tasks, its real-world applicability has been limited by the inability to ensure the safety of learned policies. We propose an approach to verifiable reinforcement learning by training decision tree policies, which can represent complex p…
A new framework for offline RL improves policy flexibility and regularity.
problem Lack of environmental interactions in offline RL leads to poor policy performance.
method Proposes a behavior-regularized implicit policy framework with modified policy-matching methods.
result The framework improves policy effectiveness and robustness beyond static datasets.
New model-based methods adapt pre-trained policies to unseen environments efficiently.
problem High sample complexity in reinforcement learning limits practical applications.
method Combines online learning and adaptive control to adapt policies in unseen environments.
result Proves policies can quickly recover trajectories from source to target environments.
A generative recurrent neural network is quickly trained in an unsupervised manner to model popular reinforcement learning environments through compressed spatio-temporal representations. The world model's extracted features are fed into compact and simple policies trained by evolution, achieving state of the art resul…
This paper improves self-play learning in games by manipulating experience distributions.
problem Improving self-play learning in games through better experience sampling.
method Three approaches: weighted sampling, Prioritized Experience Replay, and diversifying trajectories.
result Major improvements in early training performance in some games, minor improvements overall.
New algorithm for sequential off-policy learning improves performance over batch methods.
problem Training policies from logged interaction data in a sequential setting.
method Combines Logarithmic Smoothing with online PAC-Bayesian tools.
result Improves performance and accelerates convergence in sequential off-policy learning.
New method improves policies by combining Markov and non-Markov strategies.
problem Improving policies in reinforcement learning.
method Geometric Policy Composition (GPI) using a geometric horizon model (GHM).
result GPI can improve non-Markov policies by composing GHMs of base Markov policies.
Learning a policy using only observational data is challenging because the distribution of states it induces at execution time may differ from the distribution observed during training. We propose to train a policy by unrolling a learned model of the environment dynamics over multiple time steps while explicitly penali…
Study how untrained policies explore in RL environments.
problem Challenges in reinforcement learning, especially sparse or adversarial reward structures.
method Theoretical and empirical analysis of untrained deep neural policies in a toy model.
result Untrained policies generate correlated actions and non-trivial state-visitation distributions.