frt03

brax

Massively parallel rigidbody physics simulation on accelerator hardware.

d4rl

A benchmark for offline reinforcement learning.

generalized_dt

Generalized Decision Transformer for Offline Hindsight Information Matching (ICLR2022)

grok_mod_poly

Code for "Interpreting Grokked Transformers in Complex Modular Arithmetic"

inference-based-rl

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning (NeurIPS2021)

jax_dt

Minimal Decision Transformer Implementation written in Jax (Flax).

mxt_bench

A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation (ICLR2023)

pic

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning (ICML2021)

rlds_dataset_builder

An example RLDS dataset builder for X-embodiment dataset conversion.

BREMEN

Codebase of Deployment-Efficient Reinforcement Learning via Model-Based Offline Optimization (ICLR2021)

frt03/generalized_dt

Generalized Decision Transformer for Offline Hindsight Information Matching (ICLR2022)

frt03/inference-based-rl

Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning (NeurIPS2021)

frt03/jax_dt

Minimal Decision Transformer Implementation written in Jax (Flax).

frt03/mxt_bench

A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation (ICLR2023)

frt03/pic

Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning (ICML2021)

frt03/grok_mod_poly

Code for "Interpreting Grokked Transformers in Complex Modular Arithmetic"

frt03/rlds_dataset_builder

An example RLDS dataset builder for X-embodiment dataset conversion.

frt03/brax

Massively parallel rigidbody physics simulation on accelerator hardware.

frt03/d4rl

A benchmark for offline reinforcement learning.

frt03/dmc2gym

OpenAI Gym wrapper for the DeepMind Control Suite

frt03/frt03.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

frt03/gym

A toolkit for developing and comparing reinforcement learning algorithms.

frt03/xmlconvert