kaustubhsridhar's repositories
Constrained_Models
Official Code for the L4DC 2023 conference paper and ICLR 2023 NeSy-GeMs workshop paper.
time-series-OOD
Official Code for the ICCPS 2023 conference paper (nominated for best paper award) and ICML 2022 PODS workshop paper.
GPT4_fixes_reward_hacking
A simple method to fix reward hacking in the Deepmind AI Safety Gridworlds using GPT4
PoE-robustness
Official Code for the ACC 2022 paper.
checkpointing_and_recovery
ROS packages for numerical simulation of checkpointing and roll-forward recovery in case studies of Differential Drive and Car-like Ground Robots
acme
Modifications to Deepmind's acme tag 0.4.0
Awesome-Imitation-Learning
A curated list of awesome imitation learning resources and publications
baselines
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
dvrk_force_estimation
Using neural network to estimate forces on the dVRK
f1tenth_il
Implementation of various imitation learning algorithms for the F1TENTH platform
Hidden_attack_RTSS22
Official Code for the RTSS 2022 paper.
iris_exo
Transformers are Sample-Efficient World Models. Now with Exogenous components.
jat
Distributed online training of a general multi-task Deep RL Agent
multigame-dt
Implementation of Multi-Game Decision Transformers in PyTorch
OfflineRL-Kit
An elegant PyTorch offline reinforcement learning library for researchers.
pytorch_mppi
Model Predictive Path Integral (MPPI) with approximate dynamics implemented in pytorch
R2-Play
This repository is for our paper 'Read to Play (R2-Play): Decision Transformer with Multimodal Game Instruction'.
realworldrl_suite
Real-World RL Benchmark Suite
rlkit
Collection of reinforcement learning algorithms
sample-factory
High throughput synchronous and asynchronous reinforcement learning
stable-baselines3
Modifications to stable-baselines3 tag v1.8.0