Guarantees for third-person imitation learning from offline data.
problem Improving generalizability in imitation learning.
method Problem-dependent statistical learning guarantees for third-person imitation from offline observation.
result Strong performance guarantees for transferred policies in the offline setting.
A new offline RL framework unifies imitation learning and vanilla offline RL.
problem Learning from expert datasets without active data collection.
method A new offline RL framework that interpolates between imitation learning and vanilla offline RL, using a weak concentrability coefficient and a lower confidence bound algorithm.
result LCB algorithm achieves a faster rate of 1/N for nearly-expert datasets, and is adaptively optimal for the entire data composition range. Paper tackles covariate shift in offline IL using less proficient behavior data.
problem Mitigating covariate shift in Imitation Learning with limited data coverage.
method Model-based IL from Offline Data (MILO) framework.
result MILO can combat covariate shift even with sub-optimal behavior policy data.
QFIL improves offline RL by filtering data to reduce bias and variance.
problem Improving offline reinforcement learning policies with limited data.
method QFIL uses a filtered dataset to improve policies, trading off bias and variance through quantile selection.
result QFIL provides a safe policy improvement step with function approximation and effectively balances bias and variance.
New method simplifies and improves imitation learning without adversarial techniques.
problem Stable optimization and convergence issues in adversarial imitation learning methods.
method Proposes a non-adversarial framework for imitation learning, providing stronger convergence guarantees.
result Shows AIRL as a special case and derives new algorithms for offline imitation learning.
A new method for learning policies from demonstrations without reinforcement.
problem Learning policies from demonstrations without access to reinforcement signals.
method Energy-based distribution matching (EDM) to learn policy parameters and state marginals.
result EDM yields consistent performance gains over existing algorithms for strictly batch imitation learning.
Interactive IL beats BC by state-wise annotation cost.
problem Behavior Cloning struggles with annotation cost in sequential decision making.
method Proved Stagger and Warm Stagger algorithms to outperform BC.
result Interactive and hybrid IL methods outperform BC with state-wise annotation.
OSIL learns safe policies from unsafe demonstrations.
problem Offline safe imitation learning with implicit safety.
method Formulates CMDP, infers safety from non-preferred trajectories, learns cost model.
result OSIL learns safer policies without degrading reward performance.
Behavior cloning can achieve horizon-independent sample complexity in offline imitation learning.
problem Sample complexity in imitation learning increases with problem horizon.
method New analysis of behavior cloning with logarithmic loss.
result Behavior cloning can achieve linear dependence on horizon in offline IL under dense rewards.
Survey of methods for learning from observation without requiring expert actions.
problem Lack of access to expert actions in imitation learning.
method Survey and classification of state-only imitation learning (SOIL) methods.
result Identification of open problems and future research directions.
SafeMIL learns safer policies by avoiding risky behavior from non-preferred trajectories.
problem Learning safe imitation policies from non-preferred trajectories in risky environments.
method SafeMIL uses Multiple Instance Learning to learn a cost function from non-preferred trajectories.
result SafeMIL learns a safer policy that avoids non-preferred behaviors without sacrificing reward performance.
Paper optimizes GAIL for online and offline learning with linear approximations.
problem Imitation learning from expert demonstrations with linear function approximations.
method Proposes optimistic and pessimistic algorithms for online and offline settings.
result Proves optimality and efficiency of proposed algorithms.
Continuous control imitation learning fails if expert actions are smooth.
problem Continuous control imitation learning fails if expert actions are smooth.
method Study of imitation learning in discrete-time, continuous state-and-action control systems.
result Any smooth, deterministic imitator policy suffers exponentially larger error than the expert.
New algorithm robustly learns from corrupted demonstrations, even with constant fraction of noise.
problem Learning from corrupted demonstrations where a fraction of data is noise or outliers.
method Proposes a novel robust algorithm using a Median-of-Means (MOM) objective.
result Guarantees accurate policy estimation even with constant fraction of outliers, similar to classical methods in expert demonstration settings.
ORIL learns a reward function from unlabeled data to improve robot learning.
problem Leveraging unlabeled data for robot learning.
method ORIL learns a reward function from demonstrator and unlabeled trajectories, annotates data, and trains an agent via offline reinforcement learning.
result ORIL consistently outperforms BC agents on various robotic tasks.
PWIL learns agent behavior from expert using Wasserstein distance.
problem Learning agent behavior from expert demonstrations efficiently.
method Primal Wasserstein Imitation Learning (PWIL) with offline reward function.
result PWIL achieves expert behavior on MuJoCo tasks with minimal interactions.
Q-chunking improves RL for long tasks by chunking actions.
problem Improving sample efficiency and exploration in offline-to-online RL.
method Action chunking in TD-based RL methods.
result Q-chunking outperforms prior methods on long-horizon tasks.
Bayesian nonparametrics enables dynamic skill discovery from expert data.
problem Fixed K for offline skill discovery in reinforcement learning.
method Variational inference, continuous relaxations, Bayesian nonparametrics.
result Nonparametric model with dynamically-changing number of options.
Causal Imitation Learning handles noisy measurements and distribution shifts.
problem Learning from noisy state observations and distributional shifts.
method Causal inference framework and adversarial RKHS learning.
result Improved robustness to distribution shifts compared to standard methods.
Transformers learn to make decisions in new contexts from offline data.
problem Understanding when and how transformers can perform in-context reinforcement learning.
method Theoretical framework analyzing supervised pretraining for ICRL, including algorithm distillation and decision-pretrained transformers.
result Transformers can efficiently approximate optimal reinforcement learning algorithms for various environments.
New findings explain why online methods outperform offline methods in noisy expert feedback settings.
problem The challenge of learning from imperfect expert feedback in sequential decision-making systems.
method Introduced a noisy expert model and a novel variant of on-policy distillation (OPD) to address the gap between offline and online imitation learning.
result Online interaction with a noisy expert via OPD enables polynomial dependence on the horizon, unlike offline methods which require exponential growth in sample complexity.
New model shows hierarchical proof structure helps theorem provers.
problem How to efficiently learn proofs from teacher traces.
method Model proof search as MDP, analyze imitation learning from traces.
result Hierarchical proof structure leads to more efficient learning.
New technique reduces imitation learning performance gap in finite samples.
problem Imitation learning performance gap in finite samples.
method Replay estimation to reduce empirical variance in finite samples.
result Achieves optimal performance gap of $\widetilde{O} \left( \min({H^{3/2}} / {N}, {H} / {\sqrt{N}}
ight)$.
We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to evaluate what would happen if different actions were taken in the same contexts, so …
GDT improves reinforcement learning by matching future state information efficiently.
problem Efficient learning of multi-task policies from trajectory data.
method Generalized Decision Transformer (GDT) for offline hindsight information matching.
result GDT enables effective offline multi-task state-marginal matching and imitation learning.
Improves BC policies by generating new plausible trajectories.
problem Sub-optimal data quality in BC leads to poor policy performance.
method Trajectory Stitching (TS) generates new plausible transitions.
result TS significantly improves behavioural policies over original data.
Consider an imitation learning problem that the imitator and the expert have different dynamics models. Most of the current imitation learning methods fail because they focus on imitating actions. We propose a novel state alignment-based imitation learning method to train the imitator to follow the state sequences in e…
ADVISOR dynamically balances imitation and reinforcement learning to overcome the imitation gap.
problem The gap between imitation learning and reinforcement learning when teaching agents have privileged information.
method Adaptive Insubordination (ADVISOR) dynamically weights imitation and reward-based reinforcement learning losses.
result On-the-fly switching with ADVISOR outperforms pure imitation, pure reinforcement learning, and their combinations.
Compared to reinforcement learning, imitation learning (IL) is a powerful paradigm for training agents to learn control policies efficiently from expert demonstrations. However, in most cases, obtaining demonstration data is costly and laborious, which poses a significant challenge in some scenarios. A promising altern…
Reinforcement learning mimics expert behavior.
problem Learning from expert demonstrations in reinforcement learning.
method Reduction to reinforcement learning with a stationary reward.
result Expert reward can be recovered and imitation learning is bounded.
Interactive IL algorithm queries noisy expert for feedback, reducing sample size.
problem Imitation learning with noisy expert feedback requires many samples.
method Selective sampling algorithm with online regression oracle.
result Interactive IL algorithm reduces query complexity and improves performance.
New metric solves correspondence problem for robotic arm imitation learning.
problem Establishing corresponding states and actions between different robotic arms.
method Introducing a distance measure between dissimilar robotic arms and using it as a loss function.
result The distance measure effectively learns imitation policies by minimizing distance between robotic arms.
New method uses bi-level optimization to learn useful representations for imitation learning.
problem Learning useful representations for multiple tasks in imitation learning settings.
method Formulates representation learning as a bi-level optimization problem.
result Bi-level optimization framework provides sample complexity benefits for imitation learning.
Researchers improved Minecraft game performance using imitation learning.
problem Achieving state-of-the-art performance in immersive environments like Minecraft.
method Applied imitation learning to Minecraft, optimizing network architecture, loss function, and data augmentation.
result Reported stronger results than previous experiments, reaching second place in a competition.
New self-imitation learning method improves performance in continuous control tasks.
problem Improving off-policy learning in continuous control tasks.
method Proposes a n-step lower bound to generalize lower-bound Q-learning and introduces a new family of self-imitation learning algorithms.
result n-step lower bound Q-learning achieves a better trade-off between bias and contraction rate, leading to improved performance.
Paper tackles robust imitation learning from noisy demonstrations.
problem Learning from noisy demonstrations is challenging.
method Optimizes a classification risk with a symmetric loss, combining pseudo-labeling and co-training.
result Our method is more robust than state-of-the-art methods.
Paper uses Sinkhorn distances to improve imitation learning effectiveness.
problem Improving imitation learning algorithms by comparing occupancy measures.
method Formulates imitation learning as Sinkhorn distance minimization, combining optimal transport and cosine distances.
result Proposes a new critic network and transport plan that guide imitation learning.
Proof shows imitation of expert's reward and solutions in multi-objective optimization.
problem Multi-objective optimization with reward and solution imitation.
method Wasserstein inverse reinforcement learning.
result Wasserstein inverse reinforcement learning enables imitation of expert's reward and solutions in multi-objective optimization.
We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features, it does not provide an informative reward signal, leading to poor task performanc…
NDI learns from expert demonstrations by estimating occupancy measures.
problem Imitation Learning (IL) for complex systems.
method Density estimation of expert's occupancy measure followed by RL.
result NDI achieves state-of-the-art performance on control tasks.
GWIL uses Gromov-Wasserstein distance to align expert and imitation agent states.
problem Cross-domain imitation learning challenges due to different system dimensions and stationary distributions.
method Gromov-Wasserstein Imitation Learning (GWIL) using Gromov-Wasserstein distance.
result GWIL effectively aligns expert and imitation agent states in various continuous control domains.
New method improves imitation learning from expert observations.
problem Challenges in imitation learning from observation setting.
method Reparameterized Variational Divergence Minimization.
result Our method outperforms baseline approaches in low-dimensional tasks.
We describe MELEE, a meta-learning algorithm for learning a good exploration policy in the interactive contextual bandit setting. Here, an algorithm must take actions based on contexts, and learn based only on a reward signal from the action taken, thereby generating an exploration/exploitation trade-off. MELEE address…
Imitation from observation is the framework of learning tasks by observing demonstrated state-only trajectories. Recently, adversarial approaches have achieved significant performance improvements over other methods for imitating complex behaviors. However, these adversarial imitation algorithms often require many demo…
New method learns to answer questions from correct demonstrations without assuming bounded complexity of the demonstrator.
problem Learning to generate answers from correct demonstrations with multiple correct answers.
method Formalizes imitation learning in contextual bandits, relying on reward model complexity, not policy complexity.
result Achieves nearly optimal performance with sample complexity logarithmic in reward class cardinality.
Integration of reinforcement learning and imitation learning is an important problem that has been studied for a long time in the field of intelligent robotics. Reinforcement learning optimizes policies to maximize the cumulative reward, whereas imitation learning attempts to extract general knowledge about the traject…
We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imitation learning setting. We consider the generative adversarial approach to imitation learning (GAIL) and derive an optimization problem for…
Proposes a method to imitate active learning heuristics for better performance.
problem The performance of active learning heuristics depends on the classifier model and data structure.
method Imitates the selection of the best active learning heuristic using DAGGER.
result Outperforms state-of-the-art imitation learners and heuristics on well-known datasets.