Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Pieter Abbeel

Pieter Abbeel

Explaining Reinforcement Learning Policies through Counterfactual Trajectories

Jan 29, 2022
Julius Frost, Olivia Watkins, Eric Weiner, Pieter Abbeel, Trevor Darrell, Bryan Plummer, Kate Saenko

Figure 1 for Explaining Reinforcement Learning Policies through Counterfactual Trajectories

Figure 2 for Explaining Reinforcement Learning Policies through Counterfactual Trajectories

Figure 3 for Explaining Reinforcement Learning Policies through Counterfactual Trajectories

Figure 4 for Explaining Reinforcement Learning Policies through Counterfactual Trajectories

* Accepted at ICML HILL 2021 Workshop

Access Paper or Ask Questions

Target Entropy Annealing for Discrete Soft Actor-Critic

Dec 06, 2021
Yaosheng Xu, Dailin Hu, Litian Liang, Stephen McAleer, Pieter Abbeel, Roy Fox

Figure 1 for Target Entropy Annealing for Discrete Soft Actor-Critic

Figure 2 for Target Entropy Annealing for Discrete Soft Actor-Critic

Figure 3 for Target Entropy Annealing for Discrete Soft Actor-Critic

Figure 4 for Target Entropy Annealing for Discrete Soft Actor-Critic

* neurips 2021 deep rl workshop

Access Paper or Ask Questions

Zero-Shot Text-Guided Object Generation with Dream Fields

Dec 02, 2021
Ajay Jain, Ben Mildenhall, Jonathan T. Barron, Pieter Abbeel, Ben Poole

Figure 1 for Zero-Shot Text-Guided Object Generation with Dream Fields

Figure 2 for Zero-Shot Text-Guided Object Generation with Dream Fields

Figure 3 for Zero-Shot Text-Guided Object Generation with Dream Fields

Figure 4 for Zero-Shot Text-Guided Object Generation with Dream Fields

* 12 pages. Website: https://ajayj.com/dreamfields

Access Paper or Ask Questions

Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

Dec 02, 2021
Charles Packer, Pieter Abbeel, Joseph E. Gonzalez

Figure 1 for Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

Figure 2 for Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

Figure 3 for Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

Figure 4 for Hindsight Task Relabelling: Experience Replay for Sparse Reward Meta-RL

Access Paper or Ask Questions

Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning

Nov 28, 2021
Dailin Hu, Pieter Abbeel, Roy Fox

Figure 1 for Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning

Figure 2 for Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning

Figure 3 for Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning

Figure 4 for Count-Based Temperature Scheduling for Maximum Entropy Reinforcement Learning

Access Paper or Ask Questions

B-Pref: Benchmarking Preference-Based Reinforcement Learning

Nov 04, 2021
Kimin Lee, Laura Smith, Anca Dragan, Pieter Abbeel

Figure 1 for B-Pref: Benchmarking Preference-Based Reinforcement Learning

Figure 2 for B-Pref: Benchmarking Preference-Based Reinforcement Learning

Figure 3 for B-Pref: Benchmarking Preference-Based Reinforcement Learning

Figure 4 for B-Pref: Benchmarking Preference-Based Reinforcement Learning

* NeurIPS Datasets and Benchmarks Track 2021. Code is available at https://github.com/rll-research/B-Pref

Access Paper or Ask Questions

Mastering Atari Games with Limited Data

Oct 30, 2021
Weirui Ye, Shaohuai Liu, Thanard Kurutach, Pieter Abbeel, Yang Gao

Figure 1 for Mastering Atari Games with Limited Data

Figure 2 for Mastering Atari Games with Limited Data

Figure 3 for Mastering Atari Games with Limited Data

Figure 4 for Mastering Atari Games with Limited Data

* Published at NeurIPS 2021

Access Paper or Ask Questions

URLB: Unsupervised Reinforcement Learning Benchmark

Oct 28, 2021
Michael Laskin, Denis Yarats, Hao Liu, Kimin Lee, Albert Zhan, Kevin Lu, Catherine Cang, Lerrel Pinto, Pieter Abbeel

Figure 1 for URLB: Unsupervised Reinforcement Learning Benchmark

Figure 2 for URLB: Unsupervised Reinforcement Learning Benchmark

Figure 3 for URLB: Unsupervised Reinforcement Learning Benchmark

Figure 4 for URLB: Unsupervised Reinforcement Learning Benchmark

* Code for the Unsupervised Reinforcement Learning Benchmark is available at https://github.com/rll-research/url_benchmark

Access Paper or Ask Questions