← All work

Reinforcement Learning 2022

Learning from mixed-quality demonstrations

Reformulating robot imitation learning as a sequence of returns, states, and actions.

2022Repository
Decision TransformerAdapted from Figure 3t − kReturn-to-goPrevious actionStateAction distributiontReturn-to-goPrevious actionStateAction distribution···Causal transformerInput + learned position embeddingsDecision TransformerAction distributionCausal transformerState · previous action · return-to-goInputs across timesteps · adapted from Figure 3

Project description

From the original project page. Results and time references describe that version of the work.

Reformulation of Decision Transformer for Robonomic Benchmark

Reinforcement learning typically involves an agent interacting with an environment to achieve a maximum reward. Our project disregards the traditional approach of estimating policies and simplifies Reinforcement Learning to a sequence modeling problem that can effectively be solved by the Trans- former architecture. Our project extends the capabilities of the initial Decision Transformer (DT) [4] to learn from mixed- quality input data. Our modified Decision Transformer quantifies the benefit of return-conditioned imitation learning on mixed- quality data by leveraging the robomimic datasets. We show that our Decision Transformer significantly outperforms standard behavioral cloning on mixed-quality data for the Lift and Can tasks. Overall, our Decision Transformer and semi-sparse reward function provide a new way to tackle the challenges of imitation learning with mixed-quality data. Our project below is an earlier version of the paper that I plan on publishing in the upcoming future.

The question

Can an agent learn useful behavior from demonstrations of mixed quality? This project explores return-conditioned imitation learning using robomimic datasets.

The approach

Each input token concatenates the state, return-to-go and previous action. A two-layer network and learned position embeddings feed a causal transformer. Its output parameterizes an action distribution, including a five-mode Gaussian mixture policy.

The finding

The project reports improvements over behavioral cloning on the Lift and Can tasks with mixed-quality data. It also explores a semi-sparse reward function. See the report for the experimental setup.

Research status

The linked report is the project version shared on the original website. The visualization here illustrates sequence conditioning; it does not run a trained policy.

Read the paper
Open to load the paper
Text of this page