{"task":"Continuous Control","dataset":"walker.stand","metric_names":["Return"],"rows":[{"id":46478,"task":"Continuous Control","parent_task":null,"dataset":"walker.stand","model_name":"SMuZero","metrics":{"Return":"987.79"},"paper_url":"https://arxiv.org/abs/2104.06303v1","paper_title":"Learning and Planning in Complex Action Spaces","paper_date":"2021-04-13","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"metrics_order":"[\"Return\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]},{"id":46479,"task":"Continuous Control","parent_task":null,"dataset":"walker.stand","model_name":"MuZero Unplugged","metrics":{"Return":"887.2"},"paper_url":"https://arxiv.org/abs/2104.06294v1","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_date":"2021-04-13","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"metrics_order":"[\"Return\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]},{"id":83254,"task":"Continuous Control","parent_task":"3D Face Modelling","dataset":"walker.stand","model_name":"SMuZero","metrics":{"Return":"987.79"},"paper_url":"https://arxiv.org/abs/2104.06303v1","paper_title":"Learning and Planning in Complex Action Spaces","paper_date":"2021-04-13","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"metrics_order":"[\"Return\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]},{"id":83255,"task":"Continuous Control","parent_task":"3D Face Modelling","dataset":"walker.stand","model_name":"MuZero Unplugged","metrics":{"Return":"887.2"},"paper_url":"https://arxiv.org/abs/2104.06294v1","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_date":"2021-04-13","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"metrics_order":"[\"Return\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]},{"id":89960,"task":"Continuous Control","parent_task":"3D Face Modelling","dataset":"walker.stand","model_name":"SMuZero","metrics":{"Return":"987.79"},"paper_url":"https://arxiv.org/abs/2104.06303v1","paper_title":"Learning and Planning in Complex Action Spaces","paper_date":"2021-04-13","code_links":[{"title":"opendilab/LightZero","url":"https://github.com/opendilab/LightZero"}],"metrics_order":"[\"Return\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]},{"id":89961,"task":"Continuous Control","parent_task":"3D Face Modelling","dataset":"walker.stand","model_name":"MuZero Unplugged","metrics":{"Return":"887.2"},"paper_url":"https://arxiv.org/abs/2104.06294v1","paper_title":"Online and Offline Reinforcement Learning by Planning with a Learned Model","paper_date":"2021-04-13","code_links":[{"title":"DHDev0/Muzero-unplugged","url":"https://github.com/DHDev0/Muzero-unplugged"},{"title":"enpasos/muzero","url":"https://github.com/enpasos/muzero"}],"metrics_order":"[\"Return\"]","area":"Robots","uses_additional_data":0,"source":"archive","tags":[]}]}