New method learns search policies by inspecting and improving past roll-outs.
problem Learning good search policies for complex combinatorial spaces.
method Retrospective imitation learning, improving policy through past roll-outs.
result Policy can iteratively scale up to larger problems.
MineRL Competition reduced reinforcement learning sample needs.
problem Sample inefficiency in reinforcement learning.
method Human demonstrations and imitation learning integrated into reinforcement learning algorithms.
result Top solutions used deep reinforcement learning and imitation learning.
Paper proposes an algorithm to optimize CVaR using retrospective approximation and importance sampling.
problem Optimizing risk-averse problems with large sample requirements for CVaR.
method Retrospective approximation combined with importance sampling, tailored for CVaR optimization.
result The proposed algorithm reduces variance efficiently and is computationally efficient.
Retrospective and prospective analysis of Diebold-Yilmaz connectedness research.
problem Assessing the Diebold-Yilmaz approach to dynamic network connectedness.
method Retrospective and prospective analysis of Diebold-Yilmaz (2014) and personal recollections.
result Personal insights and retrospective analysis of Diebold-Yilmaz connectedness research.
We present new methods to estimate causal effects retrospectively from micro data with the assistance of a machine learning ensemble. This approach overcomes two important limitations in conventional methods like regression modeling or matching: (i) ambiguity about the pertinent retrospective counterfactuals and (ii) p…
New method aligns states for better imitation learning.
problem Different dynamics models between imitator and expert.
method State alignment-based reinforcement learning.
result Superior performance on various imitation learning settings.
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.
HGAIL learns policies without expert demonstrations.
problem Lack of expert demonstrations in imitation learning.
method Combines hindsight and GAIL to learn policies.
result Comparable performance to current methods, with curriculum learning.
New algorithm reduces sample complexity for imitation learning.
problem High sample complexity limits deployment of adversarial imitation algorithms.
method Trajectory-centric reinforcement learning ideas.
result Improved learning rate and efficiency in imitation tasks.
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.
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.
TRAIL improves robot imitation learning by focusing on task-relevant features.
problem Discriminator networks learn spurious associations, providing poor reward signals.
method Constrained discriminator optimization to learn task-relevant rewards.
result TRAIL outperforms GAIL and behaviour cloning in robotic manipulation tasks.
Estimates counterfactual outcomes linking observed and unobserved data.
problem Estimating expected counterfactual outcomes for individuals.
method Introduces retrospective counterfactual estimators and prediction intervals linking observed and unobserved outcomes.
result Retrospective counterfactual estimators and prediction intervals asymptotically satisfy valid coverage under standard causal assumptions.
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 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.
Zero-shot imitation learns to imitate tasks without expert demonstrations.
problem Learning to imitate tasks without expert supervision.
method Explore world without supervision, distill experience into goal-conditioned policy, use forward consistency loss.
result Zero-shot imitation policy can mimic expert tasks after seeing just goal demonstrations.
Study risk-sensitive imitation learning using GAIL and Wasserstein distance.
problem Improve imitation learning performance by considering risk profiles.
method Formulate risk-sensitive imitation learning, derive optimization problems for JS divergence and Wasserstein distance, develop algorithms.
result RS-GAIL algorithms outperform GAIL and RAIL in MuJoCo and OpenAI tasks.
New approach uses 'forward-looking' counterfactuals for treatment choice.
problem Using traditional 'retrospective' counterfactuals in treatment choice leads to counterintuitive results.
method Introduces 'counterfactual treatment choice' for forward-looking counterfactuals.
result Mismatches between interventional and forward-looking counterfactuals can lead to counterintuitive results.
New framework integrates imitation and reinforcement learning for better robot performance.
problem Combining reinforcement and imitation learning for intelligent robotics.
method Extends probabilistic generative model framework for reinforcement learning and develops pMDP-MO for Markov decision processes.
result Significantly better performance than reinforcement or imitation learning alone.
Study optimal investment under imitation of decision-changing rates.
problem Optimal investment under imitation of decision-changing rates.
method Proposed integral disparity to quantify imitation, derived general solution using variational method, analyzed asymptotic properties, validated with real data.
result Investor's optimal decisions under imitation of decision-changing rates.
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.
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.
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.
Extends InfoGAIL to improve imitation learning over extended periods.
problem Stable imitation of extended expert behavior from multi-modal data.
method Incorporates 'burn-in demonstrations' to condition policies at test time.
result Improves mutual information and long-term imitation of expert behavior.
New framework for multi-agent imitation learning in complex environments.
problem Multi-agent settings with multiple Nash equilibria and non-stationary environments.
method Generalized inverse reinforcement learning and actor-critic algorithm.
result Practical multi-agent imitation learning with good empirical performance.
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.
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.
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.
GASIL encourages agents to imitate past good trajectories in reinforcement learning.
problem Long-term credit assignment in sparse and delayed reward environments.
method Generative Adversarial Imitation Learning (GASIL) framework.
result GASIL improves performance in reinforcement learning tasks with delayed rewards.
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.
The paper analyzes the value discrepancies of imitation learning methods.
problem Analyzing the value discrepancies of imitation learning methods.
method Discrepancy propagation analysis for infinite-horizon settings.
result GAIL has less compounding errors than behavioral cloning.
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.
Improved online prediction with guaranteed coverage.
problem Creating reliable online predictions for arbitrary sequences.
method Online conformal prediction with decaying step sizes.
result Substantially improved practical properties, including close coverage at every time point.
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.
New method minimizes f-divergence for better imitation learning.
problem Learning from multi-modal demonstrations, especially interpolating between modes.
method Minimizing reverse KL divergence or I-projection for any f-divergence.
result Our method reliably imitates multi-modal behaviors better than existing methods.
VSCOUT detects anomalies in high-dimensional data using a hybrid VAE approach.
problem Challenges in classical SPC for high-dimensional, non-Gaussian data.
method Hybrid VAE architecture with ARD prior, ensemble filtering, and changepoint detection.
result VSCOUT achieves superior sensitivity to special-cause structure and controlled false alarms.
GAIfO learns from videos without knowing actions.
problem Learning from observation without access to actions.
method Generative adversarial networks for state-only demonstrations.
result GAIfO performs comparably to classical methods and significantly outperforms existing IfO methods.
Project reviews and compares imitation learning algorithms.
problem Achieving optimal performance by mimicking an expert's actions.
method Wide review and comparison of recent imitation learning algorithms.
result Comparison of algorithms' performance and regret bounds.
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.
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.
Unified framework for imitating tasks across domains with discrepancies.
problem Learning tasks across domains with embodiment, viewpoint, and dynamics mismatches.
method Two-step approach: alignment followed by adaptation. Alignment uses Generative Adversarial MDP Alignment (GAMA) for state and action correspondences from unpaired, unaligned demonstrations. Adaptation leverages these correspondences for zero-shot imitation.
result Effectiveness of the proposed approach in embodiment, viewpoint, and dynamics mismatch scenarios.
Paper improves AIRL by enhancing policy imitation and addressing reward recovery issues.
problem Inadequate policy imitation and limited transferable reward recovery in AIRL.
method Substituted built-in algorithm with SAC for policy updating and proposed PPO-AIRL + SAC hybrid framework.
result SAC improves policy imitation but hinders reward recovery; PPO-AIRL + SAC achieves satisfactory transfer effect.
D-REX learns reward functions from ranked demonstrations to beat the demonstrator's performance.
problem Limited performance of imitation learning compared to the demonstrator.
method Disturbance-based Reward Extrapolation (D-REX) that generates ranked demonstrations from behavioral cloning.
result D-REX significantly outperforms standard imitation learning approaches and beats the demonstrator's performance.
Relational Mimic improves visual imitation learning from video demonstrations.
problem Improving robustness and sample efficiency in visual imitation learning.
method Combines generative adversarial networks and relational learning.
result Improves agent performance in challenging locomotion tasks.
Transforms random forests into efficient neural networks using imitation learning.
problem Inefficient architectures of existing methods for transforming random forests into neural networks.
method Generates training data from a random forest and learns a neural network to imitate its behavior.
result Implicit transformation creates efficient neural networks with better generalization.
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.
A new framework estimates expert policy support to create a reward function for imitation learning.
problem Imitation learning from expert trajectories without reinforcement signals.
method Estimating the support of the expert policy to compute a fixed reward function.
result Comparable or better performance than state-of-the-art methods on discrete and continuous domains.
Recent work has demonstrated that problems-- particularly imitation learning and structured prediction-- where a learner's predictions influence the input-distribution it is tested on can be naturally addressed by an interactive approach and analyzed using no-regret online learning. These approaches to imitation learni…