Backward Learning for Goal-Conditioned Policies
Can we learn policies in reinforcement learning without rewards? Can we learn a policy just by trying to reach a goal state? We answer these questions positively by proposing a multi-step procedure that first learns a world model that goes backward in time, secondly generates goal-reaching backward trajectories, thirdly improves those sequences using shortest path finding algorithms, and finally trains a neural network policy by imitation learning. We evaluate our method on a deterministic maze environment where the observations are $64\times 64$ pixel bird's eye images and can show that it consistently reaches several goals.
Code (1)
Tasks
Imitation Learningreinforcement-learningSimilar Papers 제목 키워드 기반
Imitating Graph-Based Planning with Goal-Conditioned Policies
Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to exec…
Reinforcement Learning (RL)GHIL-Glue: Hierarchical Control with Filtered Subgoal Images
Image and video generative models that are pre-trained on Internet-scale data can greatly increase the generalization capacity of robot learning systems. These models can function as high-level planners, generating inter…
Imitation LearningVideo PredictionZero-shot GeneralizationImproving the Performance of Backward Chained Behavior Trees that use Reinforcement Learning
In this letter we show how to improve the performance of backward chained behavior trees (BTs) that use reinforcement learning (RL). BTs represent a hierarchical and modular way of combining control policies into higher …
reinforcement-learningReinforcement Learning (RL)Goal-Conditioned Generators of Deep Policies
Goal-conditioned Reinforcement Learning (RL) aims at learning optimal policies, given goals encoded in special command inputs. Here we study goal-conditioned neural nets (NNs) that learn to generate deep NN policies in f…
continuous-controlContinuous ControlFormReinforcement Learning (RL)Goal-Conditioned Imitation Learning using Score-based Diffusion Policies
We propose a new policy representation based on score-based diffusion models (SDMs). We apply our new policy representation in the domain of Goal-Conditioned Imitation Learning (GCIL) to learn general-purpose goal-specif…
DenoisingImitation LearningRobot Manipulation